devex-prd-generator
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Category 8: Indirect Prompt Injection] (LOW): The skill is designed to process untrusted user input (raw intent and notes) to generate structured documentation.
- Ingestion points: User input through the 'Mandatory intake questions'.
- Boundary markers: None specified for the input processing.
- Capability inventory: File-write capability (writing to
devex-prd.md). - Sanitization: No explicit sanitization or escaping of user input is mentioned.
- Assessment: While susceptible to indirect injection where a user might attempt to influence the agent's behavior through the 'raw intent', the risk is limited to the content of the generated markdown file.
- [Category 4: Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill does not define any Python or Node.js dependencies and does not attempt to download or execute remote scripts.
- [Category 2: Data Exposure & Exfiltration] (SAFE): There are no patterns indicating access to sensitive system files, hardcoded API keys, or unauthorized network communication.
Audit Metadata