oh-my-opencode@5.1.57
The Best AI Agent Harness - Batteries-Included OpenCode Plugin with Multi-Model Orchestration, Parallel Background Agents, and Crafted LSP/AST Tools
AI Security Review
scanned 3d ago · by lpm-firewall-aiThe flagged credential and endpoint patterns resolve to credential filtering and an authenticated, explicitly configured provider, not automatic forwarding of unrelated credentials. The install hook performs package-specific cache invalidation and binary checks; the CLI discloses anonymous telemetry and provides an opt-out.
Decision evidence
public snapshot- The manifest’s install hook runs postinstall.mjs; its prepare hook runs the build.
- The postinstall cache cleanup targets entries for this package in OpenCode’s cache.
- The skill MCP environment cleaner excludes known credentials, including Anthropic, AWS, Google, GitHub, and OpenAI keys.
- OpenGateway provider configuration is applied only when its own API key or provider authentication is present.
- The CLI discloses anonymous usage telemetry, says it excludes prompts, code, file paths, and account data, and provides an opt-out.
Source & flagged code
22 flaggedSource creates an unconsented AI-agent control surface through install-time mutation or a default unauthenticated remote skill channel.
package.jsonView on unpkg · L1Package defines install-time lifecycle scripts.
package.jsonView on unpkgFindings
Affected versions and remediation
This report applies to oh-my-opencode@5.1.57.
See all versions of oh-my-opencode for other recorded verdicts.
- Review the evidence and your use of oh-my-opencode@5.1.57 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.