compare

Pass

Audited by Gen Agent Trust Hub on Sep 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes JSON data containing excerpts and details crawled from external websites. It explicitly mitigates indirect prompt injection risks by instructing the agent to treat specific fields (findings[].excerpt and signals[].detail) as untrusted quotations and to ignore any instructions or tool calls found within them.
  • [EXTERNAL_DOWNLOADS]: The documentation provides instructions for installing the seomator-geo-audit package via uv or pipx. This package is the primary dependency for the skill's comparison functionality and aligns with the vendor's stated purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 29, 2026, 03:20 PM