render-sandbox

Warn

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS] (MEDIUM): The skill instructs the installation of the computesdk package via npm. This package and its maintainers are not included in the trusted organizations list, posing a risk of supply chain attack if the package is malicious.
  • [REMOTE_CODE_EXECUTION] (MEDIUM): The documentation suggests using npx skills add to fetch and install a skill directly from a remote GitHub repository (https://github.com/computesdk/sandbox-skills). This mechanism bypasses standard review processes and executes code from an untrusted external source.
  • [CREDENTIALS_UNSAFE] (SAFE): While the skill mentions environment variables for API keys (COMPUTESDK_API_KEY, RENDER_API_KEY), it correctly uses placeholders and does not contain hardcoded secrets.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 06:46 PM