brainstorming
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill is susceptible to indirect prompt injection because it ingests project files and history to establish context.
- Ingestion points: Project files, documentation, and recent commits are read at the start of the process.
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore instructions embedded within the ingested data.
- Capability inventory: The skill allows writing to the file system (docs/plans/), executing git commits, and triggering additional agent skills for git worktrees and implementation planning.
- Sanitization: The skill prompt does not define any validation or sanitization steps for the ingested project data.
Audit Metadata