github-automation

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

• Third-party content exposure detected (high risk: 0.90). Yes — SKILL.md explicitly requires fetching and acting on public GitHub user-generated content (issues, PRs, code, commits, and file contents) using tools such as GITHUB_LIST_REPOSITORY_ISSUES, GITHUB_GET_A_PULL_REQUEST, GITHUB_SEARCH_CODE, and GITHUB_GET_REPOSITORY_CONTENT, so untrusted third-party content on GitHub can materially influence agent decisions (e.g., merges, workflow dispatches).

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly requires connecting to Rube MCP at https://rube.app/mcp and calling RUBE_SEARCH_TOOLS at runtime to fetch current tool schemas (which directly control the agent's available instructions), making that external endpoint a required runtime dependency.