brainstorm
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified in the instructions.
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill requests access to local project files, documentation, and commit history. This is within the scope of its intended function as a brainstorming assistant and does not involve unauthorized data transmission.
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection through its data ingestion process, which is standard for context-aware development tools.
- Ingestion points: The skill reads project files, documentation, and commit history (SKILL.md).
- Boundary markers: Absent; no specific instructions to ignore instructions embedded in the project files are provided.
- Capability inventory: The skill has file-write capabilities to the docs/plans/ directory (SKILL.md).
- Sanitization: Absent; no sanitization or filtering of the ingested content is specified.
Audit Metadata