Paid Acquisition Audit
Pass
Audited by Gen Agent Trust Hub on Jul 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists exclusively of instructional content for performing a business audit and does not contain any code or executable commands.
- [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection via the processing of external marketing data.
- Ingestion points: 90-day ad performance exports and search term reports (SKILL.md).
- Boundary markers: None present in the instructions.
- Capability inventory: None. The skill does not employ any tools, scripts, or system commands.
- Sanitization: No data validation or sanitization steps are defined.
- Context: The lack of tool-use or system access prevents any practical exploitation of this surface.
Audit Metadata