marketing-council
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests data from external project files and user-provided advisor descriptions without strict validation or boundary enforcement.
- Ingestion points: The skill reads project context from
.agents/product-marketing.md,.claude/product-marketing.md, andproduct-marketing-context.md, as well as custom advisor definitions saved in.agents/advisors/. - Boundary markers: Absent. There are no instructions to use specific delimiters or to disregard potentially conflicting instructions within these external files.
- Capability inventory: The skill is capable of writing files to the
.agents/advisors/directory and utilizing external tools for web search, video analysis, and deep research. - Sanitization: Absent. No sanitization or safety-filtering logic is defined for the content loaded from context files or user-supplied advisor positions.
Audit Metadata