writing-prds
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFE
Full Analysis
- [Prompt Injection] (SAFE): No instructions were found that attempt to override agent behavior or bypass safety filters.
- [Data Exposure & Exfiltration] (SAFE): The skill uses standard file system tools (Read, Write, Glob, Grep) to manage documents within the local workspace. No sensitive file paths or unauthorized network operations were detected.
- [Remote Code Execution] (SAFE): No remote scripts or external packages are downloaded or executed.
- [Indirect Prompt Injection] (LOW):
- Ingestion points: The skill reads a local template (resources/prd.template.md) and processes user-provided feature descriptions.
- Boundary markers: None explicitly defined in the prompts, though the structured nature of the template acts as a natural constraint.
- Capability inventory: Limited to file read/write operations (Read, Write, Glob, Grep).
- Sanitization: Not applicable as the skill primarily generates text artifacts.
Audit Metadata