prd-to-issues

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for Indirect Prompt Injection. * Ingestion points: Untrusted data is retrieved from external GitHub issues using the gh issue view command (SKILL.md). * Boundary markers: There are no explicit delimiters or specific instructions to the agent to disregard commands potentially embedded within the PRD text. * Capability inventory: The skill has the ability to write to the repository using the gh issue create command (SKILL.md). * Sanitization: The skill implements a 'Quiz the user' workflow in section 4, which acts as a human-in-the-loop check to validate the output before execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 01:04 PM