oh-my-opencode@5.1.33
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 22d ago · by lpm-firewall-aiThe npm postinstall hook performs scoped cache cleanup, while the separate Codex extension update path is activated by an explicit command and refreshes package-owned plugin files and dependencies. This guarded extension setup warrants a warning; the inspected source does not establish malicious behavior.
Decision evidence
public snapshot- package.json declares a postinstall hook that runs postinstall.mjs.
- The hook removes matching OpenCode cache directories whose names begin with this package’s names.
- The launcher routes explicit lazycodex update and uninstall commands to the local Codex installer.
- Plugin refresh copies configured MCP runtimes and runs npm install or ci in a staging directory before updating the plugin.
- The LSP references to .codex paths occur in expectReject test cases.
- The inspected integration behavior is activated by a user-invoked update command; the inspected excerpts do not establish unconsented agent configuration changes or credential transfer.
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@5.1.33.
See all versions of oh-my-opencode for other recorded verdicts.
- Review the evidence and your use of oh-my-opencode@5.1.33 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.