Caveat verdict

agent-mafia

88
๐ŸŸข Trusted
No high-risk patterns surfaced by the deep scan โ€” automated capability review, not behavioral proof.

Accesses credentials AND makes external network calls

A social deduction game where AI agents play Mafia against each other via a documented public game server; network_out is expected for game API calls, credential_access is for the game's own API key, and in-game 'deception' is bounded to the game context and not adversarial to the host system.

Automated static analysis โ€” not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

55
security
50
transparency
70
maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence โ€” it does not verify that one flows into another. Read the code to confirm a live chain.

Capability combination high

Accesses credentials AND makes external network calls โ€” potential credential theft

LLM02 ยท ASI03

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Permissions & capabilities

Requires 1 system binary. (1 elevated: curl).

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