prd-to-issues

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted data from external GitHub issues using the gh issue view command.
  • Ingestion points: Data enters the agent context via the gh issue view <number> command in the 'Locate the PRD' step.
  • Boundary markers: There are no explicit boundary markers or instructions to the agent to ignore embedded commands within the fetched PRD content.
  • Capability inventory: The agent has the capability to create new GitHub issues using gh issue create based on the processed content.
  • Sanitization: The skill does not implement sanitization or validation logic for the content retrieved from the PRD before using it to generate implementation tickets.
  • [COMMAND_EXECUTION]: The skill relies on the execution of GitHub CLI commands (gh issue view, gh issue create) to perform its primary functions. While these are standard tools, they interact with external state and user-supplied issue numbers.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 02:53 PM
Security Audit — agent-trust-hub — prd-to-issues