prd
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill takes user input to generate documentation, which is a potential surface for prompt injection.
- Ingestion points: Feature descriptions and question responses are ingested from the user.
- Boundary markers: Absent; there are no delimiters to separate user input from instructions.
- Capability inventory: The skill writes Markdown files to a specific local directory (tasks/).
- Sanitization: No sanitization is performed on the user-provided feature descriptions.
- [Data Exposure & Exfiltration] (SAFE): No access to sensitive files or external network requests were found.
- [Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill does not download or execute remote scripts.
Audit Metadata