sync-merged-pr-issues

Pass

Audited by Gen Agent Trust Hub on Jul 5, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from pull request titles and bodies to perform automated actions on the issue tracker.
  • Ingestion points: Data is retrieved from the body and title fields of pull requests via gh pr list (Step 1 and 2 in SKILL.md).
  • Boundary markers: The instructions do not specify explicit delimiters or "ignore embedded instructions" markers when processing the pull request content.
  • Capability inventory: The skill can modify issue assignees and labels, post comments, and close issues using gh issue edit, gh issue comment, and gh issue close across multiple scripts.
  • Sanitization: The skill mitigates risk by using a specific regex \b...\s+#(\d+)\b to extract numeric digits only and by prioritizing GitHub's authoritative closingIssuesReferences field.
  • [COMMAND_EXECUTION]: The skill generates and executes shell commands using the GitHub CLI (gh) to perform repository management and issue reconciliation tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 5, 2026, 01:11 PM
Security Audit — agent-trust-hub — sync-merged-pr-issues