ralph-github-create-issues

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION] (SAFE): The skill uses the GitHub CLI (gh) to manage issues and labels. These operations are restricted to the current repository and follow standard development workflows.\n- [PROMPT_INJECTION] (LOW): The skill processes untrusted content from local markdown files, which represents a potential vector for indirect prompt injection.\n
  • Ingestion points: Markdown files in .claude/plans/, plans/, or prds/.\n
  • Boundary markers: Uses single-quoted bash heredocs (<<'EOF') to mitigate command injection during issue creation, but provides no natural language constraints for the processed content.\n
  • Capability inventory: Read/write/delete access on the filesystem and network interaction with the GitHub API.\n
  • Sanitization: No explicit sanitization or validation of the ingested markdown content is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:28 PM