ClawAudit verdict
ontology
ontology-knowledge-graph
The skill provides a typed knowledge graph for structured agent memory and composable skills, with auto-sync from memory files. It does not exhibit any 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. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
agent_memory
Findings (3)
Accesses system credential store
references/schema.md · code · keychain
References agent memory files
scripts/ontology_sync.py · prose · downgraded · daily_notes
Popular HTTP library — network access
scripts/ontology.py · prose · downgraded · got
Permissions & capabilities
No declared permissions — minimal attack surface.
agent_memory Is this flag fair?
Thanks — recorded.