@herjarsa/omo-meta-governor@0.29.1
Self-judging agent orchestration layer for OpenCode. Reads memory, scores sessions, dispatches decisions.
AI Security Review
scanned 24d ago · by lpm-firewall-aiThe automatic global skill installation is a concrete agent-extension lifecycle risk despite the lack of an npm install hook. The source supports a warning rather than a block because activation occurs through the extension and no active malicious behavior was identified.
Decision evidence
public snapshot- The package metadata defines build, type-check, and test scripts, with no npm install lifecycle hook.
- The primary entrypoint starts CLI synchronization unless its feature is disabled and forwards automatic-install settings.
- Both distributed entrypoints implement automatic CLI skill setup with automatic installation enabled by default and a global scope default.
- The secondary entrypoint constructs a command that adds the CLI-Anything meta-skill globally when that scope is selected.
- No npm preinstall, install, or postinstall hook was found in the package metadata.
- No direct credential collection or package-controlled network recipient was identified in the inspected paths.
Source & flagged code
7 flagged · loading sourcePackage source invokes a package manager install command at runtime.
dist/lib.jsFindings
Affected versions and remediation
This report applies to @herjarsa/omo-meta-governor@0.29.1.
See all versions of @herjarsa/omo-meta-governor for other recorded verdicts.
- Review the evidence and your use of @herjarsa/omo-meta-governor@0.29.1 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.