github-mcp-server
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a documentation and reference file for GitHub's official MCP server implementation. All external links and resources point to trusted GitHub domains, including
github.comandapi.githubcopilot.com. - [INDIRECT_PROMPT_INJECTION]: The skill documentation describes tools that ingest data from external sources such as issues, pull requests, and repository file contents. While these represent an injection surface at runtime, the skill provides explicit security guidance, including:
- Ingestion points: GitHub API responses from tools in the
repos,issues, andpull_requeststoolsets. - Boundary markers: Encourages the use of specific
toolsetsandallowedlists to restrict agent capabilities. - Capability inventory: Includes tool descriptions for reading, writing, and searching GitHub data.
- Sanitization: Advises on using read-only modes (
GITHUB_READ_ONLYorX-MCP-Readonly) to minimize impact when processing potentially untrusted content.
Audit Metadata