pypi
langchain
1 versiondiscovered · its AI-security audit & verification record by name.
0.3.9auditedresolved-commitattested-tag
coverage →langchain-ai/langchain @ 18293a4b5c6d7e8f…
AI security assessmentcleanqwen2.5-7b-instruct
Re-scan after upstream patch: prior sinks are now sanitized.
Methodology
Sources @ 18293a4b5c
README.md, libs/langchain/agents/agent.py, libs/langchain/prompts/chat.py, libs/langchain/chains/base.py, libs/langchain/tools/base.py, libs/langchain/agents/tool_calling_agent/base.py
Parts 6 files, 11840 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
History · 2 runs
- 2026-08-16clean
- 2026-08-14findingshigh2 findings
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:pypi/langchain@0.3.9 --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.
