deepen-plan
Pass
Audited by Gen Agent Trust Hub on Jul 14, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE]: The skill reads from local files in the
brand/andmarketing/directories. This behavior is documented and necessary for its primary function of context-aware plan enhancement. - [EXTERNAL_DOWNLOADS]: Mentions the use of helper agents (
mktg-audience-researcher,mktg-competitive-scanner). These are internal platform references used for delegated research tasks and do not represent untrusted external code. - [COMMAND_EXECUTION]: The skill performs file-write operations to update marketing plans and append learnings to
brand/learnings.md, which is consistent with its stated purpose. - [PROMPT_INJECTION]: The skill processes untrusted user data (existing marketing plans) without explicit boundary markers or sanitization, creating a surface for indirect prompt injection. However, the risk is minimal given the specialized marketing context and lack of sensitive system capabilities.
Audit Metadata