dot-ai-prd-create
Pass
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- Command Execution (LOW): The skill generates shell commands for
gitandgh(GitHub CLI) by interpolating user-provided variables such as[feature-name]and[issue-id]. Although this is the primary purpose of the skill and intended for documentation workflows, it relies on the underlying agent's ability to sanitize these strings to prevent command injection. - Prompt Injection (LOW): The skill has an indirect prompt injection surface.
- Ingestion points: User-provided feature descriptions and names (Step 1).
- Boundary markers: None provided in the instructions to delimit user input.
- Capability inventory: The skill executes
git add,git commit, andgit pushcommands, and interacts with the GitHub CLI. - Sanitization: There are no explicit instructions for the agent to sanitize or escape user-provided content before interpolation into shell commands or PRD files.
Audit Metadata