ClawAudit verdict
rag-retriever
The skill appears to be a retrieval-augmented generation (RAG) system for OpenClaw, allowing for document chunking, vector embedding, mixed search, and source citation. It does not contain any obvious malicious or deceptive behavior.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
package_install
Findings (3)
Dynamic import() — loads module at runtime
src/embeddings.js · prose · downgraded · import('
Popular HTTP library — network access
package-lock.json · prose · downgraded · node-fetch
Accesses sensitive environment variables
src/embeddings.js · prose · downgraded · process.env.OPENAI_API_KEY
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
package_install Is this flag fair?
Thanks — recorded.