prd-to-issues
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the official GitHub CLI (
gh) to retrieve issue details and create new work items. These operations are limited to standard issue management and are central to the skill's documented functionality. - [PROMPT_INJECTION]: Because the skill fetches content from external GitHub issues (PRDs), it is susceptible to indirect prompt injection if an attacker places malicious instructions within the PRD. However, the skill explicitly includes a human review phase ('Quiz the user') where the breakdown must be approved before issues are created, providing a critical security checkpoint.
Audit Metadata