skills/l-yifan/skills/github/Gen Agent Trust Hub

github

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The script scripts/github.ts downloads and executes the official @modelcontextprotocol/server-github package from the npm registry at runtime using npx -y.
  • [COMMAND_EXECUTION]: Uses the Bun runtime to execute a local script and spawn a child process for the GitHub MCP server using the stdio transport.
  • [DATA_EXFILTRATION]: Accesses the GITHUB_TOKEN environment variable to authenticate requests to the GitHub API, facilitating repository management as described.
  • [PROMPT_INJECTION]: The skill retrieves external data such as file contents and issue descriptions which could contain malicious instructions (indirect prompt injection surface).
  • Ingestion points: get-file-contents, get-issue, and get-pull-request in scripts/github.ts.
  • Boundary markers: None.
  • Capability inventory: High-privilege GitHub operations including file writing, branch creation, and pull request merging.
  • Sanitization: None.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 01:10 PM