brainstorming
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided ideas and project context to generate design documentation and implementation plans, creating a potential surface for indirect instructions.
- Ingestion points: User dialogue and project files (SKILL.md).
- Boundary markers: The instructions do not specify the use of delimiters or specific warnings to ignore instructions embedded in the user-provided design ideas.
- Capability inventory: The skill is capable of writing files to the
docs/plans/directory, performing git commits, and creating git worktrees. - Sanitization: There is no mention of sanitizing user input before incorporating it into the final design documents or using it to trigger subsequent agent actions.
Audit Metadata