atelier-spec-product
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- General Analysis (SAFE): The skill is entirely declarative, providing natural language frameworks (MoSCoW, User Stories, Discovery Interview) for an AI agent to use when interacting with users. It does not perform any system-level operations.
- Indirect Prompt Injection (LOW): The skill's primary function is to process untrusted user input (requirements). However, because the skill has no 'write' or 'execute' capabilities, the potential impact is limited to generating biased or incorrect documentation.
- Ingestion points: User responses during discovery interviews.
- Boundary markers: Absent; user input is interpolated directly into the requirement frameworks.
- Capability inventory: None; the skill generates text only and has no access to shell, network, or file system.
- Sanitization: None.
Audit Metadata