CLEO CLI — the assembled product consuming @cleocode/core
Soft block: AI-agent control surface
Warn by default; block when configured. The generated global instructions can influence agents using the shared AGENTS.md configuration.
AI security review
scanned · by lpm-firewall-ai
A global install automatically writes shared AI-agent instructions and installs skills outside the package. The install-time agent configuration change is an unauthorized control-surface modification.
Static reason
One or more suspicious static signals were detected.; source matched previously finalized malicious package; routed for review
Trigger
Installing @cleocode/cleo globally through npm.
Impact
The generated global instructions can influence agents using the shared AGENTS.md configuration.
Mechanism
The postinstall delegates to @cleocode/core, whose bootstrap injects a CAAMP block into ~/.agents/AGENTS.md and installs global core skills without a user-requested bootstrap.
Policy narrative
A global npm install runs a postinstall hook that calls the core bootstrap with no user-requested flag. That bootstrap automatically injects instructions into the shared ~/.agents/AGENTS.md when it is absent and installs global core skills. This changes agent configuration outside the package without separate consent.
Avoid installing @cleocode/cleo@2026.11.9. 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.