brainstorm
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface in SKILL.md.
- Ingestion points: The agent reviews the project working directory and collects user input via the AskUserQuestion tool.
- Boundary markers: No delimiters or instructions are used to isolate untrusted data from the system prompt.
- Capability inventory: The skill allows scanning project state and generating structured specifications (beads) and implementation plans.
- Sanitization: No validation or filtering of external data is performed before processing or outputting recaps.
Audit Metadata