brainstorming-skill
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill establishes a workflow where untrusted user input is processed using ideation templates and documented to the filesystem.
- Ingestion points: Untrusted data enters the agent context through user requests for brainstorming help, which are then interpolated into various templates defined in SKILL.md and supporting reference files.
- Boundary markers: The skill lacks explicit delimiters or warnings to the model to ignore potential instructions embedded within the user-provided topic or requirement strings.
- Capability inventory: The skill requires the agent to perform file-write operations to the docs/plans/ directory and execute git commits to persist the brainstorming results.
- Sanitization: No mechanisms for validation, filtering, or escaping of the user-provided strings are specified before they are processed by the agent or written to disk.
Audit Metadata