npm

@langchain/core

1 versiondiscovered · its AI-security audit & verification record by name.

0.3.18auditedresolved-commitverified
coverage →

langchain-ai/langchainjs @ a1b2c3d4e5f60718…/langchain-core

AI security assessmentcleanqwen2.5-7b-instruct

Message/prompt plumbing only; no execution sinks in the reviewed surface.

2026-08-16confidence 84%not a signed attestation — automated pre-screen
Methodology
Sources @ a1b2c3d4e5
README.md, langchain-core/src/messages/base.ts, langchain-core/src/prompts/chat.ts, langchain-core/src/runnables/base.ts, langchain-core/src/tools/index.ts, langchain-core/src/callbacks/manager.ts
Parts 6 files, 12400 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

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/%40langchain/core@0.3.18 --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.

![signet](https://signet.seekerslab.com/v1/badge/npm/%40langchain%2Fcore.svg)

← Back to the package dictionary