brainstorming

Pass

Audited by Gen Agent Trust Hub on Feb 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill is designed to ingest and analyze untrusted project data (files, documentation, and git commit history) to establish context.
  • Ingestion points: Context exploration includes reading project files, docs, and recent commits as specified in the 'Checklist' and 'Process' sections.
  • Boundary markers: Absent. The instructions do not specify delimiters or provide warnings for the agent to ignore instructions embedded within the analyzed files.
  • Capability inventory: The skill allows for writing design documents to the file system, performing git commits, and transitioning to the writing-plans skill.
  • Sanitization: No sanitization or validation of the analyzed project content is performed before it is used to influence the brainstorming dialogue.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 20, 2026, 06:05 AM