prd-start
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using git and the GitHub CLI (gh). These commands are used to create feature branches and update issue assignees, which are standard operations for development workflows.\n- [PROMPT_INJECTION]: The skill processes data from the local prds/ directory to extract parameters for shell commands, representing an indirect prompt injection surface.\n
- Ingestion points: Reads files located at prds/[issue-id]-[feature-name].md to identify the target work item.\n
- Boundary markers: The instructions do not define delimiters or specific safety instructions for handling the content of the PRD files during extraction.\n
- Capability inventory: The agent utilizes git checkout and gh issue edit based on the parsed data.\n
- Sanitization: There are no explicit instructions to validate or sanitize the issue-id or feature-name strings before they are used in command execution.
Audit Metadata