prd
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions and metadata do not contain any malicious patterns such as obfuscation, hardcoded credentials, or unauthorized network activity.
- [COMMAND_EXECUTION]: The skill orchestrates local repository tools through commands like /sc:brainstorm, /speckit.specify, and openspec validate. These operations are intended for PRD generation and restricted to the local environment.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided product ideas to generate documentation and handoff prompts. 1. Ingestion points: User input defining product/feature concepts in Phase 1 and Phase 3. 2. Boundary markers: Absent; user input is not explicitly delimited in the workflow. 3. Capability inventory: Executes local tool commands and writes files to docs/, prompts/, and workflows/ directories. 4. Sanitization: Absent; user-provided text is passed to tool workflows without explicit validation.
Audit Metadata