github-mcp

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's logic is benign and focuses on providing an interface to GitHub's official API and tools.
  • [EXTERNAL_DOWNLOADS]: The skill documentation references the ghcr.io/github/github-mcp-server Docker image. This is a reference to an official resource from a well-known service (GitHub) and is documented neutrally.
  • [DATA_EXPOSURE]: Sensitive authentication tokens are handled via environment variables (GITHUB_PERSONAL_ACCESS_TOKEN) rather than being hardcoded in scripts or configuration files.
  • [PROMPT_INJECTION]: 1. Ingestion points: The skill accesses external content from GitHub issues, pull requests, and code (SKILL.md). 2. Boundary markers: No explicit markers are defined in the provided files to delimit untrusted content. 3. Capability inventory: The skill includes Bash and Write tools (SKILL.md). 4. Sanitization: No specific sanitization logic is implemented in the provided scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 08:56 AM