opendeploy

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill makes extensive use of the @opendeploydev/cli tool to perform project analysis, resource creation, and deployment monitoring. These commands are executed locally within the agent's environment.
  • [EXTERNAL_DOWNLOADS]: The skill downloads the @opendeploydev/cli package from the npm registry. It also references an installation script for the OpenCode platform at https://raw.githubusercontent.com/opendeploy-dev/opendeploy-opencode/main/install.sh. These resources are owned and maintained by the vendor.
  • [REMOTE_CODE_EXECUTION]: An update command for the OpenCode platform involves piping a remote script to bash. This script is hosted in the vendor's official GitHub repository and is used for tool maintenance.
  • [DATA_EXFILTRATION]: Project source code and environment variables are uploaded to the vendor's dashboard at https://dashboard.opendeploy.dev/api for deployment. The skill contains strict instructions to redact sensitive values like API keys, bearer tokens, and credentials from all logs and agent responses to prevent accidental exposure.
  • [PROMPT_INJECTION]: Automated scans flagged potential concealment of information. Detailed analysis confirms these instructions are security best practices (redacting credentials and providing specific pricing information) rather than malicious attempts to bypass safety filters or hide agent behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 03:40 AM
Security Audit — agent-trust-hub — opendeploy