circleci-automation

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The skill requires the user to configure an external MCP server endpoint (https://rube.app/mcp) provided by the vendor. This endpoint serves as the interface for the CircleCI automation toolset.\n- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests untrusted data from external sources.\n
  • Ingestion points: The skill retrieves external data from CircleCI via tools such as CIRCLECI_GET_JOB_ARTIFACTS, CIRCLECI_GET_TEST_METADATA, and CIRCLECI_GET_PIPELINE_CONFIG.\n
  • Boundary markers: No delimiters or explicit instructions are provided to the agent to disregard instructions potentially embedded within the retrieved artifacts or metadata.\n
  • Capability inventory: The skill grants the agent the ability to trigger state-changing operations, including starting new CI/CD pipelines through CIRCLECI_TRIGGER_PIPELINE.\n
  • Sanitization: There is no evidence of sanitization, filtering, or validation of the data retrieved from CircleCI before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 06:58 AM