development-brainstorming
Fail
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: HIGHPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (HIGH): The skill processes untrusted external data from the project's environment to inform design decisions.
- Ingestion points: The 'Understanding the idea' phase explicitly directs the agent to check 'files, docs, recent commits'.
- Boundary markers: Absent. The skill provides no instructions to treat project content as data rather than instructions, nor does it use delimiters.
- Capability inventory: The skill has the authority to write new documentation files and commit changes to the git repository. It also triggers downstream implementation workflows.
- Sanitization: None. The skill assumes all project context is safe and legitimate.
Recommendations
- AI detected serious security threats
Audit Metadata