brainstorming
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, such as prompt injection, obfuscation, persistence, or data exfiltration, were detected in the skill instructions or metadata. The skill follows a legitimate workflow for design and documentation.
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting external project files and git history to provide context for brainstorming. This behavior is inherent to the tool's primary function and does not represent a direct security threat.
- Ingestion points: The skill reads project files, documentation, and recent git commits as specified in SKILL.md.
- Boundary markers: No explicit delimiters or boundary markers are defined for the ingested project context.
- Capability inventory: The skill possesses capabilities to write design documents to the file system (specifically
docs/plans/) and execute git operations (SKILL.md). - Sanitization: No sanitization or filtering of the ingested project data is performed.
Audit Metadata