brainstorm
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates by ingesting user-defined startup spaces, themes, and problems, which establishes a theoretical attack surface for indirect prompt injection.
- Ingestion points: User-provided themes and constraints collected during the 'Set the Frame' step in SKILL.md.
- Boundary markers: The skill does not implement specific delimiters or 'ignore' instructions for the data provided by the user.
- Capability inventory: The skill is configured to use the 'WebSearch' tool and performs file write operations to the project's '01-brainstorm/' directory.
- Sanitization: No input validation or content sanitization is defined for the user-supplied strings before they are processed.
- [NO_CODE]: The skill is composed strictly of markdown-based instructions and does not bundle any scripts, libraries, or binaries, significantly reducing the executable attack surface.
Audit Metadata