oh-my-opencode@5.1.2
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 1mo ago · by lpm-firewall-aiThe inspected code supports a bounded first-party agent-extension lifecycle risk, not malware behavior. No concrete credential theft, destructive broad mutation, remote payload execution, or nested self-lifecycle dependency was found.
Decision evidence
public snapshot- The manifest runs a postinstall script automatically.
- The postinstall script deletes matching OpenCode cache directories.
- The bundled LSP bootstrap can invoke npm install when its runtime is missing.
- The legacy installer path is limited to explicit update or uninstall commands.
- No credential collection, exfiltration, remote payload execution, or self-dependency chain was identified in the inspected paths.
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@5.1.2.
See all versions of oh-my-opencode for other recorded verdicts.
- Review the evidence and your use of oh-my-opencode@5.1.2 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.