CLEO CLI — the assembled product consuming @cleocode/core
Soft block: AI-agent control surface
Warn by default; block when configured. The injected instructions can affect AI-agent behavior across projects using the shared agent configuration.
AI security review
scanned · by lpm-firewall-ai
The global postinstall automatically writes agent instructions to the user’s shared ~/.agents/AGENTS.md file without consent. This meets the install-time AI-agent control hijack rule.
Static reason
One or more suspicious static signals were detected.; source matched previously finalized malicious package; routed for review
Trigger
Installing the package globally with npm, which runs its postinstall hook.
Impact
The injected instructions can affect AI-agent behavior across projects using the shared agent configuration.
Mechanism
The hook calls @cleocode/core bootstrap with default options; bootstrap creates a CAAMP injection block in ~/.agents/AGENTS.md when that file does not exist, without requiring a user-run setup command.
Policy narrative
A global npm install runs bin/postinstall.js, which calls @cleocode/core’s global bootstrap. The bootstrap defaults to a non-user-requested run and injects a CAAMP block into ~/.agents/AGENTS.md when that shared agent instruction file is absent. This changes agent instructions outside the package during installation without an explicit setup request.
Avoid installing @cleocode/cleo@2026.11.12. Remove it from direct dependencies and check your lockfile for transitive copies.
Choose an independently verified alternative or release. This report does not establish that other versions are safe.
If this version ran, check your AI agents' configuration and instruction files (the files this report lists) for changes you did not make, and remove them. This finding does not by itself establish malware intent.