cli-jaw@2.17.26
Personal AI assistant powered by Pi, Antigravity, AI-E, Claude, Claude E, Codex, Codex App, Cursor, Grok, Kiro, OpenCode, and Copilot — Web, Terminal, Telegram, and Discord interfaces with 107 built-in skills
AI security review
scanned · by lpm-firewall-aiThe source shows automatic execution of a downloaded shell script and activation of remotely fetched skills, but no confirmed credential theft, exfiltration, self-dependency chain, or default write to a foreign AI-agent control surface. This is a concrete dangerous lifecycle capability requiring a warning rather than a maliciousness block under the stated policy.