marketing-council
Pass
Audited by Gen Agent Trust Hub on Aug 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were identified. The skill follows best practices for simulation, including mandatory disclaimers and grounding in documented frameworks.
- [DATA_EXFILTRATION]: The skill reads project-specific context from local files (e.g.,
.agents/product-marketing.md). This is a standard functional requirement and does not involve external data transmission. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing user-provided content and project files.
- Ingestion points: User prompts,
.agents/product-marketing.md, and.claude/product-marketing.md. - Boundary markers: The skill requires a 'Simulated council' disclaimer and explicit framing of output as simulation.
- Capability inventory: File system access for reading dossiers and writing custom advisor files; text generation.
- Sanitization: Grounding rules prohibit the fabrication of quotes and endorsements, relying on the model's adherence to instructions.
Audit Metadata