Caveat verdict

production-agent-design

agent-guru

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

The skill uses network_in capability to receive data, but it is used for a legitimate purpose.

⚠ 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.

60
security
80
transparency
70
maintenance

Findings (4)

Pattern match medium

References agent memory files

references/memory-layer.md · code · MEMORY.md

Pattern match medium

Instructs covert action — may act without user awareness

references/observability-layer.md · prose · downgraded · silently

Pattern match medium

Python os.getenv — reads environment variable

references/observability-layer.md · code · os.getenv(

Pattern match medium

Python httpx request — network access

references/tool-safety-layer.md · code · httpx.get(

Permissions & capabilities

No declared permissions — minimal attack surface.

network_in

Is this flag fair?

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