github-mcp-server
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references the official GitHub MCP server Docker image hosted on the GitHub Container Registry ("ghcr.io/github/github-mcp-server"). This is an official resource from a well-known and trusted service provider.
- [INDIRECT_PROMPT_INJECTION]: The skill enables an AI agent to process data from external GitHub repositories, which represents an attack surface for indirect prompt injection.
- Ingestion points: As described in the repository operations and issue management sections of SKILL.md, the agent can read file contents, search code, and retrieve issue or pull request data.
- Boundary markers: The documentation does not specify the use of delimiters or instructions to ignore embedded prompts within the retrieved content.
- Capability inventory: The skill grants the agent capabilities to create issues, merge pull requests, and trigger GitHub Actions workflows based on the data it processes.
- Sanitization: No explicit sanitization or validation of the content retrieved from GitHub is mentioned in the configuration documentation.
Audit Metadata