ClawAudit verdict

rag

openclaw-rag-skill

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

Local RAG system using ChromaDB to index and search chat sessions and workspace files; all embeddings and retrieval are local with no external data transmission.

⚠ 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.

40
security
60
transparency
80
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (5)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · API_KEY="your-key

Pattern match medium

pip3 install — installs Python packages at runtime

SKILL.md · code · pip3 install

Pattern match medium

Instructs covert action — may act without user awareness

rag_agent.py · prose · downgraded · silently

Pattern match low

References agent memory files

SKILL.md · prose · downgraded · MEMORY.md

Pattern match low

Python os.environ.get — reads environment variable

scripts/moltbook_post.py · prose · downgraded · os.environ.get(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B). 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_installnetwork_incredential_access

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API