brainstorming

Pass

Audited by Gen Agent Trust Hub on Aug 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill reads project context which introduces an indirect prompt injection surface. Malicious instructions embedded in repository files could potentially influence the agent's brainstorming output or design decisions.
  • Ingestion points: The instructions in SKILL.md direct the agent to 'Read project state: files, docs, recent commits.'
  • Boundary markers: No delimiters or safety instructions are provided to help the agent distinguish between project data and its own core instructions.
  • Capability inventory: The skill is instructed to write documentation files and perform git operations such as committing and creating worktrees.
  • Sanitization: No validation or sanitization of ingested content is specified before the data is processed or used to generate designs.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 11, 2026, 05:08 PM
Security Audit — agent-trust-hub — brainstorming