agents-md-optimizer

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes an included Python script (scripts/audit.py) to quantify line/token counts and detect anti-patterns. This execution is limited to local file analysis and does not involve network operations or unauthorized system access.
  • [SAFE]: No evidence of prompt injection, data exfiltration, or obfuscation was found. While the skill processes untrusted instructions (ingestion points: scripts/audit.py), the risks are minimal as the logic is limited to auditing and recommendations. Boundary markers: None. Capability inventory: Local file access via agent tools. Sanitization: None. The skill's behavior matches its stated optimization purpose and adheres to security best practices.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 01:39 PM
Security Audit — agent-trust-hub — agents-md-optimizer