render
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill documents the use of the Render CLI to manage cloud services, including commands for deployment, viewing logs, and establishing SSH connections to running instances.
- [EXTERNAL_DOWNLOADS]: The skill references the @render/cli package for installation via the npm registry; this is the official tool from Render, which is a well-known cloud service provider.
- [PROMPT_INJECTION]: The skill instructions involve the agent reading and acting upon configuration files like render.yaml and package.json from the user's repository, creating a surface for indirect prompt injection if the source repository is untrusted.
- Ingestion points: Reads render.yaml, package.json, and Dockerfile from the project workspace.
- Boundary markers: No delimiters or instructions to ignore embedded prompts are present in the provided documentation.
- Capability inventory: The skill uses the Render CLI and system build tools to execute shell commands and trigger deployments.
- Sanitization: No validation or sanitization of the configuration file contents is described.
Audit Metadata