brainstorm

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the project's current state to inform its brainstorming and design process.
  • Ingestion points: The instructions direct the agent to check the current project state, including files, documentation, and recent commits.
  • Boundary markers: No specific delimiters or instructions are provided to the agent to distinguish between legitimate project content and potential embedded instructions within that content.
  • Capability inventory: The skill has the ability to update specification files directly and invoke the /add-task skill to create new task files.
  • Sanitization: There are no requirements for the agent to sanitize or validate the project data before incorporating it into designs or using it to modify files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 01:10 AM
Security Audit — agent-trust-hub — brainstorm