gsd-mvp-phase
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input to define project goals.
- Ingestion points: The workflow prompts for 'As a / I want to / So that' input via AskUserQuestion.
- Boundary markers: The skill uses structured prompts and manual confirmation gates to handle user input.
- Capability inventory: The skill is granted access to Bash, Write, and Agent tools for file management and task execution.
- Sanitization: The skill's instructions include a user-story format validation step to ensure inputs meet specific criteria.
Audit Metadata