@addai/node@0.30.5
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 has a concrete, user-impacting AI-agent control surface that suppresses safety prompts and enables persistence after daemon startup. Its lifecycle hook is limited and no self-dependency chain is present, so the source does not support a malicious-install verdict.
Decision evidence
public snapshot- Daemon startup silently accepts Claude's dangerous-permissions prompt.
- Claude session runs mark generated working directories as trusted in the user's global Claude configuration.
- Server-delivered commands can enable operating-system login persistence and perform self-updates.
- The package is an always-on remote agent daemon with authority to launch AI tools.
- The install hook only repairs execute permission on node-pty's helper.
- package.json has no runtime dependency on @addai/node itself.
- The updater restricts requested versions to semver or a dist-tag.
- No source evidence shows theft or exfiltration of unrelated local files or credentials.
Source & flagged code
11 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@0.30.5.
See all versions of @addai/node for other recorded verdicts.
- Review the evidence and your use of @addai/node@0.30.5 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.