Skills
skills/wyattowalsh/agents/skill-signing-verifier/Gen Agent Trust Hub

skill-signing-verifier

Pass

Audited by Gen Agent Trust Hub on Jul 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security risks were identified in the skill.
  • [COMMAND_EXECUTION]: The scripts/check.py file uses subprocess.run to call internal validation scripts (validate_skill.py and validate_evals.py) from a sibling project directory. This is used for local project consistency checks and does not involve untrusted data or shell injection.
  • [PROMPT_INJECTION]: The skill provides explicit instructions to the agent to avoid handling or printing private keys, and the evaluation suite confirms the agent's ability to refuse such requests.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 5, 2026, 02:05 AM
Security Audit — agent-trust-hub — skill-signing-verifier