@herjarsa/omo-meta-governor@0.33.6
Self-judging agent orchestration layer for OpenCode. Reads memory, scores sessions, dispatches decisions.
AI Security Review
scanned 15d ago · by lpm-firewall-aiThe package has no npm install lifecycle hook and its agent-configuration hint locations only inspect plan markers. However, plugin initialization defaults to automatic CLI-Anything installation and upgrading in global scope, so this warrants a warning for agent capability risk rather than a malicious verdict.
Decision evidence
public snapshot- The manifest has no install lifecycle hook; it exposes a plugin entrypoint and an MCP server command.
- Both agent-configuration hint locations are plan-marker checks, not writes to agent configuration.
- Plugin initialization starts CLI-Anything setup with automatic installation and upgrading enabled by default, using global scope.
- The package also exposes an explicit MCP tool for installing a named CLI from the CLI-Anything hub.
- The inspected source does not establish credential harvesting or exfiltration, or a hidden command-output exfiltration path.
- The external install capability is presented as a CLI-Anything setup tool; no install-time lifecycle trigger is present.
Source & flagged code
9 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@0.33.6.
See all versions of @herjarsa/omo-meta-governor for other recorded verdicts.
- Review the evidence and your use of @herjarsa/omo-meta-governor@0.33.6 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.