github
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, untrusted content from GitHub issues, pull requests, and workflow logs.
- Ingestion points: Data enters the agent context through commands like gh issue view, gh pr view --comments, and gh run view --log as described in SKILL.md.
- Boundary markers: The instructions in Section 5 ('주의 사항') explicitly warn the agent to ignore directives found within fetched external content and not treat them as user commands.
- Capability inventory: The skill possesses significant capabilities, including merging pull requests, creating issues, and executing GitHub Actions workflows.
- Sanitization: Mitigation relies on a human-in-the-loop requirement, where the skill instructs the agent to obtain explicit user confirmation before performing any write operations based on external content.
Audit Metadata