@memnexus-ai/mx-agent-cli@0.1.180
CLI for creating and managing AI agent teams
AI Security Review
scanned 4mo ago · by lpm-firewall-aiSource inspection shows a featureful AI-agent CLI, but no lifecycle execution, stealth persistence, remote payload loading, or unconsented broad control-surface mutation. Its sensitive actions are explicit command paths with visible options and safeguards.
Decision evidence
public snapshot- package.json has no preinstall/install/postinstall lifecycle hook.
- dist/index.js only dispatches explicitly invoked CLI commands.
- dist/commands/config-sync.js defaults to dry-run; writes require --apply.
- Config sync refuses dirty Git trees unless --allow-dirty and skips local edits unless --force.
- dist/commands/sync.js posts session logs only when user runs sync, to configured API URL.
- dist/lib/gh-remote.js creates/pushes a GitHub repo only with --with-remote.
Source & flagged code
5 flaggedFindings
Affected versions and remediation
This report applies to @memnexus-ai/mx-agent-cli@0.1.180.
See all versions of @memnexus-ai/mx-agent-cli for other recorded verdicts.
- Review the evidence and your use of @memnexus-ai/mx-agent-cli@0.1.180 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.