render-deploy
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the Render CLI by providing a command to download a shell script from Render's official open-source GitHub organization (render-oss).
- [REMOTE_CODE_EXECUTION]: The skill provides a command to execute the Render CLI install script via a pipe to the shell. This is a standard installation method provided by Render, a well-known cloud service provider.
- [COMMAND_EXECUTION]: The skill executes local shell commands such as git for repository management and the render CLI for infrastructure validation. It also includes instructions for the agent to request escalated sandbox permissions for deployment network calls when required by the environment.
- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it analyzes codebase files to determine application runtimes and generate render.yaml files. 1. Ingestion points: Reads project files like package.json, requirements.txt, go.mod, and source code during analysis (documented in references/codebase-analysis.md). 2. Boundary markers: Instructions advise the agent to use specific templates and validation steps. 3. Capability inventory: Performs file reads, shell command execution (git, render), and network calls via MCP tools. 4. Sanitization: Relies on Render's CLI validation (render blueprints validate) to check generated configurations.
Audit Metadata