oh-my-opencode@5.1.0
⚠ Under reviewThe Best AI Agent Harness - Batteries-Included OpenCode Plugin with Multi-Model Orchestration, Parallel Background Agents, and Crafted LSP/AST Tools
AI Security Review
scanned 1mo ago · by lpm-firewall-aiThe inspected behavior appears package-aligned and user-invoked or narrowly scoped, but a clean verdict cannot meet the mandatory fourteen-path citation coverage within the eight-citation limit. No independently supported warning or blocking behavior was established.
Decision evidence
public snapshot- The package exposes its command through a local bin wrapper.
- The postinstall cleanup targets cache entries prefixed with the package's own names.
- Both LSP QA scripts exercise rejection of malformed and out-of-scope request contexts.
- Both bundled CLI variants copy MCP runtimes only when the source configuration requests their matching argument.
- The Codex configuration workflow is exposed as an interactive install/setup command.
Source & flagged code
24 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@5.1.0.
See all versions of oh-my-opencode for other recorded verdicts.
- Review the evidence and your use of oh-my-opencode@5.1.0 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.