workflows-brainstorm
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill ingests user input via the
#$ARGUMENTSfield to define the brainstorming topic. This input is subsequently used in repository research tasks and document generation. - Ingestion points: User input is provided through the
#$ARGUMENTSvariable inSKILL.md. - Boundary markers: The input is wrapped in
<feature_description>tags to delimit it from instructions. - Capability inventory: The skill utilizes the
repo-research-analysttask for reading repository patterns and writes brainstorm documents to thedocs/brainstorms/directory. - Sanitization: No explicit instructions to ignore potentially malicious embedded commands are provided during the interpolation of user input.
Audit Metadata