render-deploy

Fail

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches the Render CLI installation script from the official Render-oss GitHub repository, which is a well-known service provider.
  • [REMOTE_CODE_EXECUTION]: Installs the Render CLI by executing a shell script retrieved from Render's official repository via a piped shell command.
  • [COMMAND_EXECUTION]: Runs local shell commands including git and render to validate configurations, manage deployments, and analyze project files.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and parses untrusted local project files (e.g., package.json, requirements.txt, go.mod) to determine deployment settings without implementing sanitization or boundary markers.
  • [PROMPT_INJECTION]: The instructions explicitly direct the agent to request escalated sandbox permissions (sandbox_permissions=require_escalated) if network access is restricted, which involves bypassing default security constraints.
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
Risk Level
HIGH
Analyzed
Feb 27, 2026, 02:02 AM