ads
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions and reference materials are purely educational and operational in nature, focusing on advertising performance and compliance.
- [EXTERNAL_DOWNLOADS]: The documentation includes code snippets for tracking pixels that reference well-known service providers (e.g., Google, Meta, LinkedIn, TikTok). These are provided as implementation references for users.
- [PROMPT_INJECTION]: The skill establishes a persona and specific output requirements (e.g., for Google RSAs) without using adversarial patterns or bypass techniques.
- [PROMPT_INJECTION]: The skill includes a surface for indirect prompt injection by instructing the agent to ingest content from external marketing files.
- Ingestion points: SKILL.md (references .agents/product-marketing.md and related context files)
- Boundary markers: None explicitly defined in the provided instructions
- Capability inventory: The skill does not include any tools or scripts with executable capabilities (subprocess, exec, etc.)
- Sanitization: No specific sanitization or filtering logic is provided for the ingested content
Audit Metadata