circleci-automation

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly retrieves and processes user-generated CircleCI content (see "Retrieve Build Artifacts" via CIRCLECI_GET_JOB_ARTIFACTS and "Review Test Results" via CIRCLECI_GET_TEST_METADATA in SKILL.md), meaning the agent ingests untrusted third-party artifact/test data that can influence subsequent decisions and actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill 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/execution.