brainstorming
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes project files and commits to establish context, which creates a potential surface for instructions embedded in those files to influence agent behavior.\n
- Ingestion points: Project files, documentation, and git history (referenced in SKILL.md).\n
- Boundary markers: Absent; the instructions do not specify delimiters for external content.\n
- Capability inventory: The skill can write to the file system, commit to git, and trigger other skills (using-git-worktrees, writing-plans).\n
- Sanitization: None; the skill does not filter or sanitize the project content before processing.\n
- Mitigation: The process requires incremental human validation (Ask after each section whether it looks right so far), which limits the impact of potential injection.
Audit Metadata