render-deploy
Fail
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: HIGHPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface (Category 8) through its codebase analysis feature.
- Ingestion points: The skill reads local project files such as package.json, requirements.txt, and go.mod (referenced in references/codebase-analysis.md and SKILL.md).
- Boundary markers: No explicit delimiters are used to isolate content during the analysis of user-provided project files.
- Capability inventory: The skill utilizes MCP tools to manage cloud resources, including create_web_service, create_postgres, and update_environment_variables.
- Sanitization: No sanitization is specified for values extracted from local files before they are processed by deployment tools.
- [EXTERNAL_DOWNLOADS]: The skill provides a command to download and execute an installation script from Render's official repository (https://raw.githubusercontent.com/render-oss/cli/main/bin/install.sh) via a pipe to the shell. This is a standard installation method for the well-known Render cloud platform.
- [COMMAND_EXECUTION]: The skill executes local shell commands such as git for repository management and the render CLI for blueprint validation and deployment operations.
Recommendations
- HIGH: Downloads and executes remote code from: https://raw.githubusercontent.com/render-oss/cli/main/bin/install.sh - DO NOT USE without thorough review
Audit Metadata