paid-ads-review
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted 'supplied exports' from advertising platforms, creating an ingestion surface where data could contain instructions meant to influence the agent. * Ingestion points: Ad performance data exports (SKILL.md). * Boundary markers: No specific delimiters or safety warnings are provided to the agent to distinguish data from instructions. * Capability inventory: Primarily read-only performance review and analysis. * Sanitization: No data validation or sanitization steps are defined for the platform exports.
Audit Metadata