brainstorming
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFE
Full Analysis
- Data Exposure (SAFE): The skill accesses local project files, documentation, and git commits. This behavior is necessary for its stated purpose of understanding project context for brainstorming.
- Indirect Prompt Injection (LOW):
- Ingestion points: Reads project files, documentation, and recent git commits (
SKILL.md). - Boundary markers: Absent; the skill does not explicitly define delimiters for external data.
- Capability inventory: Writes design documents to disk and performs git commits/worktree operations (
SKILL.md). - Sanitization: Absent; no explicit validation of ingested file content before processing.
- Command Execution (SAFE): Uses standard git operations (commit, worktrees) to manage project state. These are expected capabilities for a development-focused AI agent skill.
Audit Metadata