gh-issue-organizer

Pass

Audited by Gen Agent Trust Hub on Jul 6, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect prompt injection vulnerability surface. The skill ingests untrusted data from GitHub issue titles and bodies which can contain malicious instructions intended to manipulate the agent's behavior.
  • Ingestion points: Issue data fetched via gh issue list and gh issue view in SKILL.md.
  • Boundary markers: None specified; the agent is instructed to parse and use issue content directly.
  • Capability inventory: The skill utilizes gh, git, rg, sed, and test commands which provide significant file system and API access.
  • Sanitization: No sanitization or validation of the extracted issue content is performed before use.
  • [COMMAND_EXECUTION]: The skill uses shell commands with parameters derived directly from external issue content, creating a potential command injection vector.
  • Evidence: In SKILL.md Step 4, extracted strings like <symbol>, <function>, and <file-path> are passed to rg, sed, and git commands (e.g., rg -n "<symbol>|<function>|<type>" .).
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 6, 2026, 07:18 AM
Security Audit — agent-trust-hub — gh-issue-organizer