CLEO CLI — the assembled product consuming @cleocode/core
Soft block: AI-agent control surface
Warn by default; block when configured. Changes agent instructions and adds global agent skills without an explicit user command, creating an AI-agent control hijack risk.
AI security review
scanned · by lpm-firewall-ai
A global install automatically runs bootstrap that writes agent instructions and installs global skills without an explicit user command. This meets the install-time AI-agent configuration hijack rule.
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
Changes agent instructions and adds global agent skills without an explicit user command, creating an AI-agent control hijack risk.
Mechanism
The postinstall calls core bootstrap with no user-requested flag; bootstrap defaults that flag to false, creates or injects into ~/.agents/AGENTS.md when needed, and installs CLEO skills globally.
Policy narrative
A global npm install triggers postinstall bootstrap without an explicit user request. The bootstrap can create and populate ~/.agents/AGENTS.md and install CLEO skills globally, modifying agent configuration outside the package directory.
Avoid installing @cleocode/cleo@2026.11.11. 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.