brainstorming
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- Indirect Prompt Injection (LOW): The skill is susceptible to indirect prompt injection because it incorporates external data into the agent's context.
- Ingestion points: Instructions in SKILL.md direct the agent to check project files, docs, and recent commits.
- Boundary markers: Absent; there are no instructions to delimit or ignore instructions found within project data.
- Capability inventory: Natural language dialogue, design generation, and architectural analysis.
- Sanitization: Absent; the skill does not include steps to sanitize or validate project files before processing.
Audit Metadata