github-automation

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill establishes an attack surface for indirect prompt injection by ingesting untrusted data from GitHub sources while possessing high-impact write permissions.
  • Ingestion points: Data is retrieved from external sources via GITHUB_LIST_REPOSITORY_ISSUES, GITHUB_GET_A_PULL_REQUEST, GITHUB_GET_REPOSITORY_CONTENT, and GITHUB_SEARCH_CODE (defined in SKILL.md).
  • Boundary markers: The instructions lack explicit delimiters or "ignore instructions" directives to isolate external content from agent prompts.
  • Capability inventory: The skill possesses high-impact capabilities including GITHUB_MERGE_A_PULL_REQUEST, GITHUB_DELETE_A_REPOSITORY, and GITHUB_UPDATE_BRANCH_PROTECTION (defined in SKILL.md).
  • Sanitization: No sanitization or validation of content fetched from the GitHub API is specified.
  • [EXTERNAL_DOWNLOADS]: The skill requires a connection to a remote MCP server at https://rube.app/mcp to access automation tools and manage GitHub OAuth authentication. This endpoint is the vendor's primary infrastructure for the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 07:51 AM