github-automation

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the user to add an external MCP server URL (https://rube.app/mcp) to their client configuration. This introduces a dependency on a third-party service not managed by the primary platform, which is required for the skill's core functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data from external sources and possesses powerful administrative capabilities, creating a vulnerability surface for indirect prompt injection.
  • Ingestion points: Untrusted data enters the agent context through tools like GITHUB_LIST_REPOSITORY_ISSUES, GITHUB_GET_A_PULL_REQUEST, GITHUB_SEARCH_CODE, and GITHUB_GET_REPOSITORY_CONTENT as described in SKILL.md.
  • Boundary markers: The instructions do not define specific delimiters or warnings to ignore instructions embedded within the GitHub data being processed.
  • Capability inventory: The skill includes tools for sensitive operations such as GITHUB_MERGE_A_PULL_REQUEST, GITHUB_CREATE_A_WORKFLOW_DISPATCH_EVENT, GITHUB_UPDATE_BRANCH_PROTECTION, and GITHUB_DELETE_A_REPOSITORY.
  • Sanitization: There are no documented procedures for sanitizing or validating the content retrieved from GitHub before it influences the agent's decision-making process.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 02:44 PM
Security Audit — agent-trust-hub — github-automation