brainstorming
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process project context, including files, documentation, and commit history. This creates a potential surface for indirect prompt injection if external data contains malicious instructions, though this is the core intended functionality of the skill.
- Ingestion points: Processes project files, documentation, and recent git commits (SKILL.md).
- Boundary markers: The skill does not explicitly define delimiters or specific safety instructions for handling untrusted data contents.
- Capability inventory: File system write access (writing design docs to
docs/plans/), git operations (committing designs), and invocation of related workspace management skills (SKILL.md). - Sanitization: No explicit sanitization or filtering of external content is described.
Audit Metadata