Caveat verdict
ontology-engineer
Local-only ontology extraction with explicit security model: no external API calls, mandatory user confirmation before scanning, local-only output artifacts.
⚠ 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.
Permission integrity
file_read+write
Findings (5)
Pipe to python — executes piped content as Python code
references/formats-and-deps.md · prose · downgraded · | python
References sudo — requests elevated privileges
references/formats-and-deps.md · code · sudo
Python shutil file operation — copies/moves/deletes files
references/formats-and-deps.md · code · shutil.rmtree(
subprocess execution — runs system commands from Python
scripts/convert_doc.py · prose · downgraded · subprocess.run(
References agent configuration files
references/knowledge-graph-workflow.md · prose · downgraded · CLAUDE.md
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.
file_write Is this flag fair?
Thanks — recorded.