write-a-prd
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads untrusted data from the repository and configuration files.
- Ingestion points: The agent explores the repository (Step 2) and reads the
CLAUDE.mdfile to detect issue tracker configurations. - Boundary markers: The skill lacks explicit instructions or delimiters to isolate repository content from the agent's core instructions, potentially allowing malicious content in the codebase to influence agent behavior.
- Capability inventory: The skill can execute shell commands (
gh issue create) and invoke external MCP tools (createJiraIssue). - Sanitization: There is no evidence of sanitization or filtering of the data retrieved from the codebase before it is used to generate the PRD or passed to issue-creation tools.
- [COMMAND_EXECUTION]: The skill uses the GitHub CLI (
gh) to perform actions. - Evidence: The skill specifies the use of
gh issue createto submit the generated PRD if GitHub is the detected issue tracker.
Audit Metadata