marketing-council
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies and processes untrusted user input and external research data, which creates a vulnerability surface for indirect prompt injection.
- Ingestion points: Untrusted data enters the agent context through user-provided marketing questions and external web content fetched during the optional 'Live Research Pass'.
- Boundary markers: The skill requires a mandatory simulation disclaimer ('> Simulated council') and uses structured markdown headers to help differentiate between generated perspectives and system instructions.
- Capability inventory: The skill utilizes network-enabled tools for research and possesses the capability to write files to the local project directory (specifically '.agents/advisors/').
- Sanitization: No explicit sanitization, validation, or escaping of the ingested external content is described in the skill instructions.
Audit Metadata