prd
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data when updating existing Product Requirements Documents.
- Ingestion points: Reads markdown files from local directories like
requirements/,prds/, andspecs/(SKILL.md). - Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded prompts within the PRD files being read.
- Capability inventory: The skill performs file read and write operations to manage document state.
- Sanitization: There is no evidence of content validation or sanitization for data read from the filesystem.
- [SAFE]: No other threat patterns, such as remote code execution, credential exfiltration, or obfuscation, were detected. The file operations are consistent with the skill's primary purpose of document management.
Audit Metadata