oh-my-opencode@5.1.24
⚠ 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 28d ago · by lpm-firewall-aiThe inspected excerpts do not independently establish malicious behavior, and the flagged dynamic function call is part of validator generation. A clean verdict requires citations for 14 distinct paths, which exceeds the 8-citation limit, so this requires manual review.
Decision evidence
public snapshot- package.json defines a postinstall hook that runs postinstall.mjs.
- postinstall.mjs removes matching oh-my-opencode and oh-my-openagent entries from the OpenCode cache.
- The two LSP QA scripts point their configuration paths into a home directory used for isolated QA.
- Both CLI bundles copy an MCP runtime only when its source argument appears in the project’s .mcp.json.
- The inspected new Function call generates a validator from schema code.
- The launcher imports child_process to start the selected platform binary.
Source & flagged code
23 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@5.1.24.
See all versions of oh-my-opencode for other recorded verdicts.
- Review the evidence and your use of oh-my-opencode@5.1.24 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.