prd-to-issues

Pass

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core functionality of reading external data.\n
  • Ingestion points: The skill ingests untrusted data from GitHub issue descriptions and comments using the gh issue view command.\n
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore or isolate potential instructions embedded within the fetched PRD content.\n
  • Capability inventory: The skill provides the agent with write access to the GitHub repository via the gh issue create command.\n
  • Sanitization: No evidence of sanitization, filtering, or validation is present to prevent the execution of malicious instructions contained within the retrieved PRD.\n
  • Mitigation: The process includes a human review step ('Quiz the user') which requires explicit approval of the drafted issues before any write operations occur, significantly lowering the risk of automated exploitation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 2, 2026, 04:30 AM