github-automation

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

• Third-party content exposure detected (high risk: 0.90). The skill's Core Workflows and "Search Code and Commits" sections explicitly require calling GitHub APIs (e.g., GITHUB_SEARCH_CODE, GITHUB_GET_REPOSITORY_CONTENT, GITHUB_LIST_REPOSITORY_ISSUES, GITHUB_FIND_PULL_REQUESTS) to fetch user-generated code, issues, PRs and file contents that the agent is expected to read and act on (e.g., decide merges or trigger workflows), which exposes it to untrusted third-party content that could inject instructions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires connecting at runtime to the external MCP server https://rube.app/mcp (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.