npm
langchain
1 versiondiscovered · its AI-security audit & verification record by name.
0.3.7unauditedresolved-commitverified
coverage →langchain-ai/langchainjs @ a1b2c3d4e5f60718…/libs/langchain
Audits exist at this commit, but none touch /libs/langchain — they cover other packages in this monorepo, so this package is not audited by them.
AI security assessmentcleanqwen2.5-7b-instruct
JS agent toolkit mirrors the patched Python paths; tool output is not executed.
Methodology
Sources @ a1b2c3d4e5
README.md, langchain/src/agents/agent.ts, langchain/src/agents/executor.ts, langchain/src/tools/base.ts, langchain/src/chains/base.ts, langchain/src/memory/base.ts
Parts 6 files, 12900 bytes
Techniques llm-static-source-review, prompt-injection-detection, insecure-tool-and-function-calling, unsafe-eval-exec-of-model-output, ssrf-detection, secret-exposure-detection, classic-software-vulnerability-review
Parameters qwen2.5-7b-instruct · temp 0 · max 900 tok · local
classes examined: CWE-77
Independently verified by
Gate this package in CI
Fail the build on an attested vulnerability or registry tampering, and emit skip-scan excludes for audited files — one command against the registry.
signet gate --purl pkg:npm/langchain@0.3.7 --registry https://signet.seekerslab.com
README badge
Show this package's Signet status in its README — audited, AI pre-screened, or unaudited. Updates within an hour of a new attestation.
