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[].excerptandsignals[].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-auditpackage viauvorpipx. This package is the primary dependency for the skill's comparison functionality and aligns with the vendor's stated purpose.
Audit Metadata