github

Pass

Audited by Gen Agent Trust Hub on Mar 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill facilitates the execution of numerous GitHub CLI (gh) commands for repository, issue, and pull request management. These are legitimate administrative and development operations within the scope of the skill's purpose.\n- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection.\n
  • Ingestion points: Untrusted data enters the agent context through commands like gh pr view, gh pr list --comments, gh issue view, and gh run view --log, which retrieve user-controlled text from external GitHub resources (SKILL.md).\n
  • Boundary markers: There are no instructions to the agent to treat retrieved content as data only or to ignore instructions embedded in the retrieved text.\n
  • Capability inventory: The skill provides high-impact capabilities such as merging pull requests (gh pr merge), deleting releases (gh release delete), and running workflows (gh workflow run) (SKILL.md).\n
  • Sanitization: No automated sanitization or validation of fetched content is performed before it is processed by the agent.\n- [EXTERNAL_DOWNLOADS]: The skill includes functionality to clone repositories and download release assets from GitHub. These operations use a well-known service and are documented here as part of the intended functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 15, 2026, 11:09 AM
Security Audit — agent-trust-hub — github