paid-media-creative-strategist
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from ad platforms and competitor libraries to inform its creative generation, which creates a potential surface for indirect prompt injection.
- Ingestion points: Competitor ad library research and existing campaign performance metrics (SKILL.md).
- Boundary markers: The instructions do not define delimiters or specific guidance to ignore commands potentially embedded in ad content.
- Capability inventory: The skill uses Google Ads tools to pull data and deploy creative variations (SKILL.md).
- Sanitization: No sanitization or validation of the processed ad copy is mentioned.
Audit Metadata