circleci-automation

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

• Third-party content exposure detected (low risk: 0.10). The skill’s required runtime workflow only calls CircleCI toolkit tools with user-supplied IDs/filters (pipelines/workflows/job_number) and does not include any step where the agent ingests arbitrary outsider-authored free text without first selecting a specific CircleCI item.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires adding the MCP endpoint https://rube.app/mcp which is contacted at runtime (e.g., via RUBE_SEARCH_TOOLS) to fetch tool schemas that directly control agent behavior/prompts, and the skill depends on that external server.