@herjarsa/omo-meta-governor@0.35.5
⚠ Under reviewSelf-judging agent orchestration layer for OpenCode. Reads memory, scores sessions, dispatches decisions.
AI Security Review
scanned 12d ago · by lpm-firewall-aiThe inspected agent helpers perform local plan checks, and skill installation is gated by explicit confirmation. The required archive could not be reviewed as source, so the package remains unresolved and requires manual review.
Decision evidence
public snapshot- The manifest lists build and test scripts, with no install lifecycle hook.
- The indicated agent-configuration locations in dist/index.js and dist/lib.js contain the same local AGENTS.md plan check and completion-marker helper.
- The MCP skill installer requires confirm=true before running the package-install command.
- The package includes dist/skills/chore.tar.gz, whose contents were not verifiable as UTF-8 source.
- The MCP server exposes a skill-install operation that runs npx skills add after confirmation.
Source & flagged code
9 flagged · loading sourcePackage source invokes a package manager install command at runtime.
dist/lib.jsView on unpkg · L2Findings
Affected versions and remediation
This report applies to @herjarsa/omo-meta-governor@0.35.5.
See all versions of @herjarsa/omo-meta-governor for other recorded verdicts.
- Review the evidence and your use of @herjarsa/omo-meta-governor@0.35.5 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.