Caveat verdict
chronicle-monograph-memory
The skill provides a legitimate functionality for long-term semantic memory backed by ChromaDB and local Ollama embeddings, with no evidence of malicious behavior.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (3)
Accesses OpenClaw config/secrets directly
scripts/memory.py · prose · downgraded · ~/.openclaw/openclaw.json
Popular HTTP library — network access
scripts/memory.py · prose · downgraded · got
References agent memory files
scripts/memory.py · prose · downgraded · MEMORY.md
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.