@addai/node@0.30.7
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 2mo ago · by lpm-firewall-aiThe package does not show a malicious install hook or confirmed data theft, but daemon startup suppresses Claude safety prompts and mutates global trust settings. Its automatic self-update compounds that capability by accepting later package releases without a per-update user action.
Decision evidence
public snapshot- Launching the daemon automatically accepts Claude's dangerous-permissions warning in the user's settings.
- Claude session handling marks requested working directories as trusted in the user's global Claude configuration.
- The daemon periodically checks for a newer release and rolls itself when the version differs.
- The self-update path globally installs a selected @addai/node release.
- The install-time hook only invokes a local node-pty helper-permission repair.
- Startup persistence is behind the explicit ainode startup enable command.
- No credential exfiltration or hidden remote payload execution was confirmed from the inspected paths.
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@0.30.7.
See all versions of @addai/node for other recorded verdicts.
- Review the evidence and your use of @addai/node@0.30.7 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.