render-automation
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the configuration of an external MCP server at https://rube.app/mcp which provides the underlying toolkit.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection.
- Ingestion points: The skill ingests untrusted data such as service names and deployment metadata from the Render platform via RENDER_LIST_SERVICES and RENDER_RETRIEVE_DEPLOY in SKILL.md.
- Boundary markers: There are no delimiters or instructions provided in SKILL.md to distinguish untrusted external data from system instructions.
- Capability inventory: The skill can perform state-changing operations including triggering new deployments via RENDER_TRIGGER_DEPLOY in SKILL.md.
- Sanitization: No data validation or sanitization logic is present in SKILL.md to filter the content of retrieved cloud metadata before it is processed by the agent.
Audit Metadata