skill-scanner

Pass

Audited by Gen Agent Trust Hub on Aug 9, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes external files to perform security audits, creating an indirect prompt injection surface where untrusted data could influence agent behavior.\n
  • Ingestion points: Files within the target skill directory processed during manual and automated scan phases.\n
  • Boundary markers: None. The instructions do not define explicit delimiters for content read from external skills.\n
  • Capability inventory: File system listing, reading content, and executing a bundled Python script.\n
  • Sanitization: None. The skill relies on the agent's manual evaluation of intent rather than programmatic sanitization.\n- [COMMAND_EXECUTION]: The skill executes a bundled Python script (scripts/scan_skill.py) to perform static analysis. This is a legitimate use of local command execution consistent with the skill's stated purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 9, 2026, 11:24 PM
Security Audit — agent-trust-hub — skill-scanner