github
Pass
Audited by Gen Agent Trust Hub on Apr 24, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE]: The skill reads repository information, issue content, and file contents from GitHub via the official API to provide repository management capabilities.
- [INDIRECT_PROMPT_INJECTION]: The skill reads data from external sources such as GitHub issues and pull requests, which could contain untrusted instructions. However, the instructions explicitly require the agent to obtain user confirmation before executing any write operations, mitigating the risk of unauthorized actions. * Ingestion points: github_get_issue, github_get_pull, github_get_file, and github_search_code in SKILL.md. * Boundary markers: None defined. * Capability inventory: github_create_branch, github_push_files, and github_create_pull_request in SKILL.md. * Sanitization: Not mentioned.
Audit Metadata