spec-writer
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions are limited to gathering information and formatting it into a PRD. No dangerous command execution, persistence mechanisms, or credential theft patterns were found.
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves processing external data (user stories, research, and docs), which represents a surface for indirect prompt injection. 1. Ingestion points: SKILL.md indicates the skill collects a rich problem description and encourages users to paste existing context. 2. Boundary markers: None explicitly defined to separate user-provided context from system instructions. 3. Capability inventory: The skill generates text documentation and does not have access to subprocesses, network operations, or file-writing tools. 4. Sanitization: No input sanitization or filtering is specified.
Audit Metadata