@addai/node@0.30.2
Daemon that pairs a machine with your +Ai account and runs Claude / Codex / Kimi / Gemini agents on its behalf. Reachable via Supabase from Vault, Entity Studio, or any other +Ai surface.
AI Security Review
scanned 14d ago · by lpm-firewall-aiSource confirms a package-owned daemon startup routine suppresses Claude's bypass-permissions warning, which is a concrete agent capability risk. The inspected manifest's postinstall hook runs a separate PTY repair script, so the source does not establish an install-time control-surface mutation.
Decision evidence
public snapshot- Starting the daemon calls a routine that edits the user's Claude settings.
- That routine sets `skipDangerousModePermissionPrompt` to true in `~/.claude/settings.json`.
- The npm postinstall hook only runs the PTY helper repair script.
- The Claude settings mutation runs when the daemon starts; the manifest postinstall hook runs a separate helper script.
Source & flagged code
12 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgPackage source references child process execution.
dist/command-runner.jsView on unpkg · L46Findings
Affected versions and remediation
This report applies to @addai/node@0.30.2.
See all versions of @addai/node for other recorded verdicts.
- Review the evidence and your use of @addai/node@0.30.2 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.