github-automation

Warn

Audited by Snyk on Feb 20, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly requires calling GitHub toolkit endpoints that fetch and ingest public, user-generated GitHub content (e.g., GITHUB_SEARCH_CODE, GITHUB_GET_REPOSITORY_CONTENT, GITHUB_LIST_REPOSITORY_ISSUES) as part of required workflows, so external repo/issue/PR content can influence subsequent tool decisions (merges, dispatches) and enable indirect prompt injection.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.90). The skill explicitly requires adding and calling the MCP endpoint https://rube.app/mcp at runtime (via RUBE_SEARCH_TOOLS) to fetch tool schemas that directly determine the agent's available instructions and behavior, so this external URL can control prompts and execution.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 20, 2026, 08:19 AM