github-automation

Pass

Audited by Gen Agent Trust Hub on Apr 8, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests untrusted data from GitHub and has the capability to perform sensitive actions.
  • Ingestion points: The skill uses tools like GITHUB_LIST_REPOSITORY_ISSUES, GITHUB_SEARCH_CODE, and GITHUB_GET_REPOSITORY_CONTENT to fetch content from external repositories, issues, and pull requests.
  • Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions embedded within the fetched GitHub data.
  • Capability inventory: The skill possesses high-privilege capabilities, including GITHUB_MERGE_A_PULL_REQUEST, GITHUB_CREATE_A_WORKFLOW_DISPATCH_EVENT, and GITHUB_DELETE_A_REPOSITORY (referenced in pitfalls).
  • Sanitization: The instructions do not include requirements for sanitizing or validating external data before it is processed by the agent.
  • [EXTERNAL_DOWNLOADS]: The skill requires connecting to an external Model Context Protocol (MCP) server at https://rube.app/mcp. This endpoint acts as the gateway for the GitHub automation toolkit.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 8, 2026, 09:39 AM