to-prd
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes data from the project codebase (ADRs, CONTEXT.md) to generate PRDs, creating a surface for indirect prompt injection. However, this is part of its core documentation synthesis function.\n
- Ingestion points: Reads files and project context using Read, Grep, and Glob tools (SKILL.md).\n
- Boundary markers: None explicitly defined to separate external data from system instructions.\n
- Capability inventory: The skill uses tools including Bash, Write, and Edit.\n
- Sanitization: No specific sanitization of ingested content is described.\n- [COMMAND_EXECUTION]: The skill documentation references the execution of local environment tools for setup and maintenance.\n
- Evidence: The Compatibility and References sections mention running the configuration command
setup-matt-pocock-skillsand the local validator script.agent-skills/skill-standardization/scripts/validate_skill.sh.
Audit Metadata