opencode-cli
Fail
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill recommends an automated installation method that pipes a remote script directly into the shell:
curl -fsSL https://opencode.ai/install | bash. This executes unverified code from an external server, a high-risk pattern that can be exploited if the domain or transport is compromised. - [EXTERNAL_DOWNLOADS]: Instructions include the installation of global packages from third-party registries and taps, specifically the
opencode-aipackage via npm/pnpm and theanomalyco/tap/opencoderepository via Homebrew. These resources originate from unverified external entities. - [COMMAND_EXECUTION]: The documentation provides patterns for an agent to programmatically execute shell commands using
exec(). This allows the agent to trigger arbitrary functionality in theopencodeCLI, including attaching to local network services (e.g.,http://localhost:4096), which increases the attack surface for local network interaction.
Recommendations
- HIGH: Downloads and executes remote code from: https://opencode.ai/install - DO NOT USE without thorough review
- AI detected serious security threats
Audit Metadata