render-automation

Warn

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The setup instructions direct users to configure a third-party MCP server at https://rube.app/mcp within their client environment.
  • [REMOTE_CODE_EXECUTION]: By adding the remote MCP server, the agent relies on an external provider for tool definitions and logic. This creates a supply-chain dependency where tool execution is controlled by the remote service.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it ingests data from the Render API and uses it to drive agent workflows.
  • Ingestion points: Service and project data retrieved via RENDER_LIST_SERVICES and RENDER_LIST_PROJECTS (SKILL.md).
  • Boundary markers: The instructions do not define delimiters or warnings to ignore embedded instructions in API responses.
  • Capability inventory: The agent can perform high-impact actions like RENDER_TRIGGER_DEPLOY based on this external data.
  • Sanitization: No input validation or output sanitization is specified for data returned by the Render toolkit.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 10, 2026, 07:49 AM
Security Audit — agent-trust-hub — render-automation