CVE trackerNIST NVD and CISA KEV, refreshed every 6 hours

Self-hosted AI vulnerabilities, live.

Every CVE that NIST NVD publishes for the 20 components self-hosted AI stacks actually run: agents like OpenClaw, inference servers like Ollama and vLLM, apps like Open WebUI, Langflow and n8n, vector databases and orchestration libraries. Exploited-in-the-wild entries come from CISA KEV. Newest entry: 30 Oct 2026.

2,098CVEs on the 20 components
178published, last 30 days
13critical, last 30 days
13exploited in the wild

These four numbers and every list on this page come from the same set: the CVEs that are about one of the 20 components below, each counted once. A CVE that affects two components is on both component pages. A CVE in a third-party tool that only mentions a component is not counted.

Recent security advisories

Published in the last 7 days, newest first, from NIST NVD and CISA KEV.

CVE-2026-119978high 8.5Flowise: Sandbox escape vulnerability that lets authenticated users execute OS commandsFlowise through 3.1.4 contains a sandbox escape vulnerability that allows authenticated users to execute OS commands by abusing allowlisted langchain and mammoth modules when…30 Oct 2026CVE-2026-119557medium 5.9n8n: Path traversal in the Databricks noden8n from 2.14.0 through 2.46.3 contains a path traversal vulnerability in the Databricks node that allows unauthenticated attackers to reach arbitrary Databricks API endpoints by…30 Oct 2026CVE-2026-119408high 8.8n8n: Remote code execution in deprecated Functionn8n before 2.42.6, 2.43.x before 2.43.3, and 3.x before 3.0.1 contains a remote code execution vulnerability via deprecated Function, Function Item, and LangChain Code nodes…30 Oct 2026CVE-2026-93680critical 9.8Langflow: Authentication bypass via improper authenticationIBM Langflow OSS 1.0.0 through 1.12.8 could allow a remote attacker to bypass security restrictions due to improper authentication.29 Oct 2026CVE-2026-90991medium 6.5Langflow: Authenticated denial of service via allocation of resources without limitsIBM Langflow OSS 1.0.0 through 1.12.4 could allow a remote authenticated attacker to cause a denial of service due to allocation of resources without limits or throttling.29 Oct 2026CVE-2026-77819medium 6.5Langflow: Authenticated overwrite arbitrary files via path traversalIBM Langflow OSS 1.0.0 through 1.12.3 could allow a remote authenticated attacker to overwrite arbitrary files due to improper limitation of a pathname to a restricted directory.29 Oct 2026CVE-2026-77817medium 6.5Langflow: Authenticated information disclosure (exposure of sensitive information)IBM Langflow OSS 1.0.0 through 1.12.4 could allow a remote authenticated attacker to obtain sensitive information due to improper sanitization of secrets during flow and project…29 Oct 2026CVE-2026-18894medium 6.5Langflow: Trigger pre-existing stored Python component code in a public workflow, executing itIBM Langflow OSS 1.0.0 through 1.12.4 could allow a remote attacker to trigger pre-existing stored Python component code in a public workflow, executing it under the flow owner's…29 Oct 2026CVE-2026-110309high 8.8Langflow: Authenticated OS command execution via improper control of code generationIBM Langflow OSS 1.0.0 through 1.12.4 could allow a remote authenticated attacker to execute arbitrary commands due to improper control of code generation.29 Oct 2026CVE-2026-110245high 7.5Langflow: Information disclosure via improper authenticationIBM Langflow OSS 1.0.0 through 1.12.4 could allow a remote attacker to obtain sensitive information due to improper authentication.29 Oct 2026CVE-2026-110244high 8.8Langflow: Authenticated information disclosure via path traversalIBM Langflow OSS 1.0.0 through 1.12.4 could allow a remote authenticated attacker to obtain sensitive information due to improper limitation of a pathname to a restricted…29 Oct 2026CVE-2026-110200medium 6.5Langflow: Authenticated information disclosure via cleartext storage of sensitive informationIBM Langflow OSS 1.0.0 through 1.12.4 could allow a remote authenticated attacker to obtain sensitive information due to cleartext storage of sensitive information.29 Oct 2026CVE-2026-110196high 8.8Langflow: Could allow a remote attacker with a low-privileged authenticated account (missing authorization)IBM Langflow OSS 1.0.0 through 1.12.4 could allow a remote attacker with a low-privileged authenticated account to bypass the administrator-only restriction and execute arbitrary…29 Oct 2026CVE-2026-110193high 8.8Langflow: Could allow a remote attacker with a low-privileged authenticated account (code injection)IBM Langflow OSS 1.0.0 through 1.12.8 could allow a remote attacker with a low-privileged authenticated account to cause the Agentic Assistant to generate or submit component code…29 Oct 2026CVE-2026-110192medium 6.5Langflow: Authenticated information disclosure via insufficiently protected credentialsIBM Langflow OSS 1.0.0 through 1.12.8 could allow a remote authenticated attacker to obtain sensitive information due to insufficiently protected credentials.29 Oct 2026CVE-2026-110190medium 6.5Langflow: Authenticated directory traversalIBM Langflow OSS 1.0.0 through 1.12.4 could allow an authenticated user to traverse directories on the system. An attacker could send a specially crafted URL request to view…29 Oct 2026CVE-2026-110186critical 9.8Langflow: Code execution via improper control of code generationIBM Langflow OSS 1.0.0 through 1.12.8 could allow a remote attacker to execute arbitrary code due to improper control of code generation.29 Oct 2026CVE-2026-107329critical 9.9Langflow: Authenticated code execution via improper control of code generationIBM Langflow OSS 1.0.0 through 1.12.4 could allow a remote authenticated attacker to execute arbitrary code due to improper control of code generation.29 Oct 2026CVE-2026-107328critical 9.9Langflow: Authenticated code execution via improper neutralization of code in eval/execIBM Langflow OSS 1.0.0 through 1.12.4 could allow a remote authenticated attacker to execute arbitrary code due to improper neutralization of code in eval/exec.29 Oct 2026CVE-2026-107327critical 9.9Langflow: Authenticated code execution via missing authorizationIBM Langflow OSS 1.0.0 through 1.12.4 could allow a remote authenticated attacker to execute arbitrary code due to missing authorization.29 Oct 2026

Exploited in the wild

All 13 on CISA's Known Exploited Vulnerabilities catalog, most severe first. Patch these first.

CVE-2025-68613critical 9.9n8n: Critical Remote Code Execution (RCE) in their workflow expression evaluation systemn8n is an open source workflow automation platform. Versions starting with 0.211.0 and prior to 1.120.4, 1.121.1, and 1.122.0 contain a critical Remote Code…Exploited in the wild, on CISA KEV19 Dec 2025CVE-2026-9198critical 9.8Langflow: Lets unauthenticated attackers chain /api/v1/auto_login with /api/v1/validate/codeIBM Langflow OSS 1.0.0 through 1.10.0 allows unauthenticated attackers to chain /api/v1/auto_login (mints SUPERUSER tokens to any network caller) with…Exploited in the wild, on CISA KEV17 Jul 2026CVE-2026-42208critical 9.8LiteLLM: A database query used during proxy API key checks mixed the caller-supplied key valueLiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.81.16 to before version 1.83.7, a database query used…Exploited in the wild, on CISA KEV8 May 2026CVE-2026-33017critical 9.8Langflow: The POST /api/v1/build_public_tmp/{flow_id}/flow endpoint allows building public flowsLangflow is a tool for building and deploying AI-powered agents and workflows. In versions prior to 1.9.0, the POST /api/v1/build_public_tmp/{flow_id}/flow…Exploited in the wild, on CISA KEV20 Mar 2026CVE-2026-0770critical 9.8Langflow: Remote Code Execution via exec_globalsLangflow exec_globals Inclusion of Functionality from Untrusted Control Sphere Remote Code Execution Vulnerability. This vulnerability allows remote attackers…Exploited in the wild, on CISA KEV23 Jan 2026CVE-2025-3248critical 9.8Langflow: Code injection in the /api/v1/validate/code endpointLangflow versions prior to 1.3.0 are susceptible to code injection in the /api/v1/validate/code endpoint. A remote and unauthenticated attacker can send…Exploited in the wild, on CISA KEV7 Apr 2025CVE-2026-64849critical 9.3MLflow: The unauthenticated POST /api/2.0/mlflow/webhooks/{id}/test endpoint calls _validate_webhook_urlMLflow is an open source AI engineering platform for agents, large language models, and machine learning models. Starting in 3.3.0 and prior to 3.15.0, the…Exploited in the wild, on CISA KEV17 Aug 2026CVE-2026-42271high 8.8LiteLLM: Two endpoints used to preview an MCP serverLiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.74.2 to before version 1.83.7, two endpoints used to…Exploited in the wild, on CISA KEV8 May 2026CVE-2026-33634high 8.8LiteLLM: 2026, a threat actor used compromised credentialsTrivy is a security scanner. On March 19, 2026, a threat actor used compromised credentials to publish a malicious Trivy v0.69.4 release, force-push 76 of 77…Exploited in the wild, on CISA KEV23 Mar 2026CVE-2025-34291high 8.8Langflow: Chained vulnerability that enables account takeover and remote code executionLangflow versions up to and including 1.6.9 contain a chained vulnerability that enables account takeover and remote code execution. An overly permissive CORS…Exploited in the wild, on CISA KEV5 Dec 2025CVE-2025-62593high 8.8Ray: Developers working with Ray as a development tool can be exploitedRay is an AI compute engine. Prior to version 2.52.0, developers working with Ray as a development tool can be exploited via a critical RCE vulnerability…Exploited in the wild, on CISA KEV26 Nov 2025CVE-2026-55255high 8.4Langflow: Insecure Direct Object Reference (IDOR) in /api/v1/responses endpointLangflow is a tool for building and deploying AI-powered agents and workflows. Prior to 1.9.1, an Insecure Direct Object Reference (IDOR) vulnerability in…Exploited in the wild, on CISA KEV23 Jun 2026CVE-2026-59822high 8.2LiteLLM: MCP Streamable HTTP endpoint allowed an unauthenticated attackerLiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.84.0, LiteLLM's MCP Streamable HTTP endpoint allowed an…Exploited in the wild, on CISA KEV8 Jul 2026

CVEs per component

All-time count on NVD, the last 90 days, and CISA KEV entries. Busiest first.

AI app / builderLangflow CVEs239 total, 141 in 90 days 6 KEVAI app / buildern8n CVEs234 total, 109 in 90 days 1 KEVAgentOpenClaw CVEs661 total, 78 in 90 daysModel servingvLLM CVEs131 total, 75 in 90 daysAI app / builderFlowise CVEs151 total, 59 in 90 daysAI app / builderOpen WebUI CVEs176 total, 55 in 90 daysLocal inferencellama.cpp CVEs48 total, 27 in 90 daysMLOpsMLflow CVEs91 total, 12 in 90 days 1 KEVOrchestration libraryLangGraph CVEs19 total, 9 in 90 daysLLM gatewayLiteLLM CVEs48 total, 8 in 90 days 4 KEVModel servingNVIDIA Triton Inference Server CVEs66 total, 8 in 90 daysLocal inferenceOllama CVEs32 total, 5 in 90 daysOrchestration libraryLangChain CVEs52 total, 3 in 90 daysAI app / builderAnythingLLM CVEs73 total, 2 in 90 daysAI app / builderLibreChat CVEs51 total, 0 in 90 daysOrchestration libraryAutoGen CVEssee listOrchestration libraryRay CVEs10 total, 0 in 90 days 1 KEVVector databaseQdrant CVEs6 total, 0 in 90 daysVector databaseWeaviate CVEs5 total, 0 in 90 daysVector databaseChroma CVEs6 total, 0 in 90 days

Not counted above: 56 CVEs on agents we follow outside these 20 components (Hermes Agent 33, Nanobot 10, NanoClaw 10, IronClaw 2, ZeroClaw 1). They are listed on each agent's page.

Read in depth

CVEs we wrote up by hand.

Latest 50 CVEs

The archive, newest first. Every entry has its own page with affected versions and the fix.

Get alerts on your stack

CVE-2026-119978high 8.5Flowise: Sandbox escape vulnerability that lets authenticated users execute OS commandsFlowise through 3.1.4 contains a sandbox escape vulnerability that allows authenticated users to execute OS commands by abusing allowlisted langchain and…30 Oct 2026CVE-2026-119557medium 5.9n8n: Path traversal in the Databricks noden8n from 2.14.0 through 2.46.3 contains a path traversal vulnerability in the Databricks node that allows unauthenticated attackers to reach arbitrary…30 Oct 2026CVE-2026-119408high 8.8n8n: Remote code execution in deprecated Functionn8n before 2.42.6, 2.43.x before 2.43.3, and 3.x before 3.0.1 contains a remote code execution vulnerability via deprecated Function, Function Item, and…30 Oct 2026CVE-2026-93680critical 9.8Langflow: Authentication bypass via improper authenticationIBM Langflow OSS 1.0.0 through 1.12.8 could allow a remote attacker to bypass security restrictions due to improper authentication.29 Oct 2026CVE-2026-90991medium 6.5Langflow: Authenticated denial of service via allocation of resources without limitsIBM Langflow OSS 1.0.0 through 1.12.4 could allow a remote authenticated attacker to cause a denial of service due to allocation of resources without limits or…29 Oct 2026CVE-2026-77819medium 6.5Langflow: Authenticated overwrite arbitrary files via path traversalIBM Langflow OSS 1.0.0 through 1.12.3 could allow a remote authenticated attacker to overwrite arbitrary files due to improper limitation of a pathname to a…29 Oct 2026CVE-2026-77817medium 6.5Langflow: Authenticated information disclosure (exposure of sensitive information)IBM Langflow OSS 1.0.0 through 1.12.4 could allow a remote authenticated attacker to obtain sensitive information due to improper sanitization of secrets…29 Oct 2026CVE-2026-18894medium 6.5Langflow: Trigger pre-existing stored Python component code in a public workflow, executing itIBM Langflow OSS 1.0.0 through 1.12.4 could allow a remote attacker to trigger pre-existing stored Python component code in a public workflow, executing it…29 Oct 2026CVE-2026-110309high 8.8Langflow: Authenticated OS command execution via improper control of code generationIBM Langflow OSS 1.0.0 through 1.12.4 could allow a remote authenticated attacker to execute arbitrary commands due to improper control of code generation.29 Oct 2026CVE-2026-110245high 7.5Langflow: Information disclosure via improper authenticationIBM Langflow OSS 1.0.0 through 1.12.4 could allow a remote attacker to obtain sensitive information due to improper authentication.29 Oct 2026CVE-2026-110244high 8.8Langflow: Authenticated information disclosure via path traversalIBM Langflow OSS 1.0.0 through 1.12.4 could allow a remote authenticated attacker to obtain sensitive information due to improper limitation of a pathname to a…29 Oct 2026CVE-2026-110200medium 6.5Langflow: Authenticated information disclosure via cleartext storage of sensitive informationIBM Langflow OSS 1.0.0 through 1.12.4 could allow a remote authenticated attacker to obtain sensitive information due to cleartext storage of sensitive…29 Oct 2026CVE-2026-110196high 8.8Langflow: Could allow a remote attacker with a low-privileged authenticated account (missing authorization)IBM Langflow OSS 1.0.0 through 1.12.4 could allow a remote attacker with a low-privileged authenticated account to bypass the administrator-only restriction…29 Oct 2026CVE-2026-110193high 8.8Langflow: Could allow a remote attacker with a low-privileged authenticated account (code injection)IBM Langflow OSS 1.0.0 through 1.12.8 could allow a remote attacker with a low-privileged authenticated account to cause the Agentic Assistant to generate or…29 Oct 2026CVE-2026-110192medium 6.5Langflow: Authenticated information disclosure via insufficiently protected credentialsIBM Langflow OSS 1.0.0 through 1.12.8 could allow a remote authenticated attacker to obtain sensitive information due to insufficiently protected credentials.29 Oct 2026CVE-2026-110190medium 6.5Langflow: Authenticated directory traversalIBM Langflow OSS 1.0.0 through 1.12.4 could allow an authenticated user to traverse directories on the system. An attacker could send a specially crafted URL…29 Oct 2026CVE-2026-110186critical 9.8Langflow: Code execution via improper control of code generationIBM Langflow OSS 1.0.0 through 1.12.8 could allow a remote attacker to execute arbitrary code due to improper control of code generation.29 Oct 2026CVE-2026-107329critical 9.9Langflow: Authenticated code execution via improper control of code generationIBM Langflow OSS 1.0.0 through 1.12.4 could allow a remote authenticated attacker to execute arbitrary code due to improper control of code generation.29 Oct 2026CVE-2026-107328critical 9.9Langflow: Authenticated code execution via improper neutralization of code in eval/execIBM Langflow OSS 1.0.0 through 1.12.4 could allow a remote authenticated attacker to execute arbitrary code due to improper neutralization of code in eval/exec.29 Oct 2026CVE-2026-107327critical 9.9Langflow: Authenticated code execution via missing authorizationIBM Langflow OSS 1.0.0 through 1.12.4 could allow a remote authenticated attacker to execute arbitrary code due to missing authorization.29 Oct 2026CVE-2026-107326high 8.8Langflow: Authenticated code execution via OS command injectionIBM Langflow OSS 1.0.0 through 1.12.4 could allow a remote authenticated attacker to execute arbitrary code due to improper neutralization of special elements…29 Oct 2026CVE-2026-104339critical 9.8Langflow: Code execution via OS command injectionIBM Langflow OSS 1.0.0 through 1.12.3 could allow a remote attacker to execute arbitrary code due to improper neutralization of special elements used in an OS…29 Oct 2026CVE-2026-104331medium 5.4Langflow: Server-side request forgery (SSRF)IBM Langflow OSS 1.0.0 through 1.12.3 is vulnerable to server-side request forgery (SSRF). This may allow an authenticated attacker to send unauthorized…29 Oct 2026CVE-2026-104328high 8.8Langflow: Authenticated code execution via OS command injectionIBM Langflow OSS 1.0.0 through 1.12.3 could allow a remote authenticated attacker to execute arbitrary code due to improper neutralization of special elements…29 Oct 2026CVE-2026-104324high 8.8Langflow: Authenticated code execution via deserialization of untrusted dataIBM Langflow OSS 1.0.0 through 1.12.3 could allow a remote authenticated attacker to execute arbitrary code due to deserialization of untrusted data.29 Oct 2026CVE-2026-104317high 8.1Langflow: Could allow a remote attacker who could reach the message broker to execute arbitrary codeIBM Langflow OSS 1.0.0 through 1.12.3 could allow a remote attacker who could reach the message broker to execute arbitrary code on the system due to the…29 Oct 2026CVE-2026-104316medium 6.5Langflow: Authenticated cancel any victim's running background workflow job by sending a single HTTP requestIBM Langflow OSS 1.0.0 through 1.12.3 could allow an authenticated attacker to cancel any victim's running background workflow job by sending a single HTTP…29 Oct 2026CVE-2026-104315medium 4.3Langflow: Server-side request forgery (SSRF)IBM Langflow OSS 1.0.0 through 1.12.3 is vulnerable to server-side request forgery (SSRF). This may allow an authenticated attacker to send unauthorized…29 Oct 2026CVE-2026-104314medium 6.5Langflow: Could allow an authenticated attacker with a read or share grant on a target flowIBM Langflow OSS 1.0.0 through 1.12.3 could allow an authenticated attacker with a read or share grant on a target flow to retrieve the flow owner's stored…29 Oct 2026CVE-2026-104312low 3.5Langflow: Authenticated produce a server-generated ZIP archive containing entry paths that traverseIBM Langflow OSS 1.0.0 through 1.12.3 could allow an authenticated attacker to produce a server-generated ZIP archive containing entry paths that traverse…29 Oct 2026CVE-2026-104310medium 4.3Langflow: Authenticated information disclosure via server-side request forgeryIBM Langflow OSS 1.0.0 through 1.12.3 could allow a remote authenticated attacker to obtain sensitive information due to a server-side request forgery (SSRF)…29 Oct 2026CVE-2026-104309medium 6.5Langflow: Authenticated information disclosure via path traversalIBM Langflow OSS 1.0.0 through 1.12.3 could allow a remote authenticated attacker to obtain sensitive information due to improper limitation of a pathname to a…29 Oct 2026CVE-2026-104308medium 4.3Langflow: Authenticated denial of service via OS command injectionIBM Langflow OSS 1.0.0 through 1.12.3 could allow a remote authenticated attacker to cause a denial of service due to improper neutralization of special…29 Oct 2026CVE-2026-103092high 8.5Langflow: Authenticated execute arbitrary SQL commands via improper access controlIBM Langflow OSS 1.0.0 through 1.12.3 could allow a remote authenticated attacker to execute arbitrary SQL commands due to improper access control.29 Oct 2026CVE-2026-102590medium 5Langflow: Authenticated information disclosure via server-side request forgeryIBM Langflow OSS 1.0.0 through 1.12.3 could allow a remote authenticated attacker to obtain sensitive information due to a server-side request forgery…29 Oct 2026CVE-2026-101288high 8.8Langflow: Authenticated code execution via code injectionIBM Langflow OSS 1.0.0 through 1.12.3 could allow a remote authenticated attacker to execute arbitrary code due to improper neutralization of special elements…29 Oct 2026CVE-2026-119052high 7.5llama.cpp: Uncaught exception in the ggml-rpc serverllama.cpp b2877 before b11935 contains an uncaught exception vulnerability in the ggml-rpc server that allows unauthenticated remote attackers to crash the…29 Oct 2026CVE-2026-118668high 8.6LangGraph (langgraph-api): Authorization bypass through a user-controlled keylanggraph-api implements the LangGraph API for rapid development and testing. From 0.1.2 until 0.15.0, JavaScript or TypeScript custom authentication Store…28 Oct 2026CVE-2026-118667medium 4.3LangGraph (langgraph-sdk): From langgraph 1.2.3 until 1.2.14LangGraph Python SDK is used to connect to running LangGraph API servers, manage assistants, threads and stream runs from Python applications. From…28 Oct 2026CVE-2026-118679high 7.5n8n: Server-side request forgery in the Slack Trigger webhookn8n before 1.123.83, 2.41.4, and 2.42.1 contains a server-side request forgery vulnerability in the Slack Trigger webhook that allows unauthenticated attackers…28 Oct 2026CVE-2026-118678high 7.1n8n: Prototype pollution vulnerability that lets low-privileged users alter built-in object behaviourn8n before 2.41.4 and 2.42.x before 2.42.1 contains a prototype pollution vulnerability that allows low-privileged users to alter built-in object behaviour by…28 Oct 2026CVE-2026-118677medium 5.9n8n: Missing confirmation in the Local Gateway desktop appn8n before 2.41.4 and 2.42.x before 2.42.1 contains a missing confirmation vulnerability in the Local Gateway desktop app that allows its deep-link connect…28 Oct 2026CVE-2026-118676high 7.1n8n: Authorization bypass vulnerability that lets member users use credentials they cannot accessn8n before 1.123.85, 2.43.5, and 2.44.1 contains an authorization bypass vulnerability that allows member users to use credentials they cannot access by…28 Oct 2026CVE-2026-118675high 7.1n8n: Credential guard bypass vulnerabilityn8n before 1.123.85, 2.43.5, and 2.44.1 contains a credential guard bypass vulnerability that allows editors of shared workflows to use restricted credentials…28 Oct 2026CVE-2026-118649high 8.3n8n: Accepts a client-supplied workflow ID and caches each workflow's owner project in memory by that IDn8n before 2.43.5 and 2.44.x before 2.44.1 accepts a client-supplied workflow ID and caches each workflow's owner project in memory by that ID, so a crafted ID…28 Oct 2026CVE-2026-118648high 7.3n8n: Contains a stored cross-site scripting vulnerabilityn8n before 1.123.85, 2.x before 2.43.5, and 2.44.x before 2.44.1 contains a stored cross-site scripting vulnerability because some webhook response paths, such…28 Oct 2026CVE-2026-118647high 8.2n8n: Saves the SeaTable Trigger node's API token in error execution datan8n before 1.123.85, 2.x before 2.43.5, and 2.44.x before 2.44.1 saves the SeaTable Trigger node's API token in error execution data, because failed poll…28 Oct 2026CVE-2026-118646medium 6.5n8n: Regular expression denial of service vulnerabilityn8n before 1.123.85, 2.43.5, and 2.44.1 contains a regular expression denial of service vulnerability that allows authenticated members to block the event loop…28 Oct 2026CVE-2026-118645high 8.7n8n: Filter injection in the Quick Base noden8n before 1.123.85, 2.x before 2.43.5, and 2.44.x before 2.44.1 contains a filter injection vulnerability in the Quick Base node, which sends the Where filter…28 Oct 2026CVE-2026-118644high 7.7n8n: Passes a failed workflow's full execution contextn8n before 2.41.5 and 2.42.x before 2.42.2 passes a failed workflow's full execution context, including the identity of the user who started the run, to the…28 Oct 2026
Also on PocketClaw

More AI security tools

AI agents trackerOpenClaw, Hermes, Nanobot and the restAI hardwareHosts for self-hosted AIAI providersOpenRouter, Anthropic, OpenAIAI guidesLong-form breakdowns and playbooksAI comparisonsSide-by-side breakdownsAI glossaryEvery term, defined