to-prd
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is to read local project information, including files, repository structure, and conversation history, to synthesize a Product Requirements Document (PRD). The results are saved to a local
docs/folder. The skill does not perform any network operations, access sensitive credentials, or execute arbitrary system commands. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from multiple external sources including user-provided files, repository contents, and conversation history (Ingestion points: SKILL.md). While there are no explicit boundary markers or sanitization processes mentioned to prevent the agent from obeying instructions hidden in these sources, the skill's capabilities are restricted to file reading and generating markdown documentation (Capability inventory: File read, file write). This creates a low-risk surface for indirect prompt injection that does not lead to significant security compromise.
Audit Metadata