@herjarsa/omo-meta-governor@0.34.1
Self-judging agent orchestration layer for OpenCode. Reads memory, scores sessions, dispatches decisions.
AI Security Review
scanned 15d ago · by lpm-firewall-aiInspected source does not establish malicious behavior. The manifest has no install lifecycle hook, and the flagged agent-related locations inspect plan markers rather than alter agent configuration.
Decision evidence
public snapshot- package.json declares no install lifecycle scripts and exposes the bundled entrypoints.
- The indicated index.js and lib.js locations check project plan markers; they do not mutate agent configuration.
- The MCP skill installation tool requires confirm=true before proceeding.
- Startup skill sync returns immediately when the feature is disabled in project configuration.
- lib.js runs package-manager commands for optional codegraph setup, but the inspected install routine is an explicit runtime capability, not an npm lifecycle hook.
- The MCP server uses network access for skill search and downloads; inspected code shows explicit confirmation for skill installation and a configuration gate for startup sync.
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@0.34.1.
See all versions of @herjarsa/omo-meta-governor for other recorded verdicts.
- Review the evidence and your use of @herjarsa/omo-meta-governor@0.34.1 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.