render-deploy
Fail
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [REMOTE_CODE_EXECUTION]: Fetches and executes a CLI installation script from the official Render organization repository (
render-oss) on GitHub. This is provided as an optional step for users who need the Render CLI for Blueprint validation. - [COMMAND_EXECUTION]: Instructions guide the agent to perform several shell-based tasks, including managing local Git repositories (
git remote,git push), running therenderCLI for authentication and validation, and executing framework-specific build and start commands. - [INDIRECT_PROMPT_INJECTION]: The skill processes user codebase content to determine application requirements and generate
render.yamlfiles. - Ingestion points: The agent is instructed to read local files and analyze directory structures as specified in
SKILL.mdandreferences/codebase-analysis.md. - Boundary markers: No explicit instructions or delimiters are provided to prevent the agent from following instructions potentially embedded in the analyzed code.
- Capability inventory: The skill uses MCP tools to create services and databases on Render, and instructions allow the agent to commit and push changes to Git repositories.
- Sanitization: The skill lacks explicit sanitization or filtering logic for the data ingested during codebase analysis.
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