Caveat verdict

astroclaw

45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.

The skill explicitly instructs agents to fetch uncontrolled external content daily from astroclaw.xyz and use it to 'subtly influence generations' and 'break deterministic loops', making the agent's behavior dependent on arbitrary third-party server responses — a persistent external influence vector on agent cognition.

⚠ 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.

85
security
90
transparency
90
maintenance

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Permissions & capabilities

No declared permissions — minimal attack surface.

network_out

Is this flag fair?

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