wechat-bro@1.6.8
AI agent interface for WeChat Web — send/receive messages, manage contacts, upload media, transcribe voice
AI Security Review
scanned 26d ago · by lpm-firewall-aiThe install hook performs package-aligned Puppeteer browser setup, and the inspected source uses WeChat session data for WeChat media uploads. No concrete malicious behavior was established in the required source paths.
Decision evidence
public snapshot- The postinstall hook configures Puppeteer’s Chromium cache under the package’s data directory and installs Chrome there if missing.
- During agent dispatch, the orchestrator links or copies the selected agent file to the task directory’s AGENTS.md.
- Media uploads use WeChat upload parameters and send the session cookie to the resulting upload URL.
- The CLI’s daemon setup runs when started in daemon mode or as a plain TTY run.
Source & flagged code
7 flaggedInstall-time lifecycle script matches a deterministic static-gate block pattern.
package.jsonView on unpkgPackage defines install-time lifecycle scripts.
package.jsonView on unpkgA bounded semantic-analysis stage reached its safety limit; remaining detectors completed, but this package requires AI review.
package.jsonView on unpkgFindings
Affected versions and remediation
This report applies to wechat-bro@1.6.8.
See all versions of wechat-bro for other recorded verdicts.
- Review the evidence and your use of wechat-bro@1.6.8 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.