create-git-issue

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface through its data ingestion process.\n
  • Ingestion points: Fetches issue bodies and comments from external references or URLs in Step 2.\n
  • Boundary markers: No explicit delimiters or instructions to treat external issue content as untrusted data are provided.\n
  • Capability inventory: Utilizes gh CLI for network operations and shell execution; writes prd.md and issues.md to the workspace root.\n
  • Sanitization: No explicit sanitization or validation of the fetched issue content is performed before interpolation into generated drafts.\n- [COMMAND_EXECUTION]: The skill provides shell command templates that incorporate variables derived from user input or external content.\n
  • Evidence: The instruction to use gh issue create --title "<PRD title>" relies on the agent for proper escaping. While double quotes are specified in the template, the absence of explicit sanitization for shell metacharacters within titles or filenames presents a vulnerability surface.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 04:54 PM