aicodeman@1.29.0
Mission control for AI coding agents - run 20 autonomous agents with real-time monitoring and session persistence
AI Security Review
scanned 1mo ago · by lpm-firewall-aiThe package contains concrete unconsented install-time mutations and background execution, so it should warn. The inspected credential use is tied to a guarded Anthropic voice relay rather than demonstrated theft.
Decision evidence
public snapshot- The install hook starts a detached web server automatically.
- The install hook overwrites the consumer repository's pre-commit hook.
- The install path can rebuild and modify node-pty.
- At runtime, the voice feature reads a Claude OAuth token and relays it to Anthropic.
- No self-dependency or downloaded payload was found in package.json.
- The credential relay is guarded by same-origin checks and voice availability.
- The reviewed network endpoint is Anthropic's voice service, not an unrelated collector.
Source & flagged code
29 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgInstall-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkgPackage source references child process execution.
dist/ai-checker-base.jsView on unpkg · L24Findings
Affected versions and remediation
This report applies to aicodeman@1.29.0.
See all versions of aicodeman for other recorded verdicts.
- Review the evidence and your use of aicodeman@1.29.0 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.