Caveat verdict
memory-optimization
Memory management optimization skill providing templates and local scripts for structured agent memory; all operations are local file management with no external network calls.
⚠ 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
agent_memory
Findings (5)
Possible hardcoded credential
SKILL.md · code · API_KEY="your-glm-token
References agent memory files
SKILL.md · code · MEMORY.md
References agent configuration files
CLAUDE.md · code · CLAUDE.md
subprocess execution — runs system commands from Python
tests/test_memory_ontology_cli.py · prose · downgraded · subprocess.run(
Python os.environ.get — reads environment variable
scripts/kg_extractor.py · prose · downgraded · os.environ.get(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B/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.
agent_memory Is this flag fair?
Thanks — recorded.