wechat-bro@1.6.3
AI agent interface for WeChat Web — send/receive messages, manage contacts, upload media, transcribe voice
AI Security Review
scanned 2mo ago · by lpm-firewall-aiThis is a real dangerous agent-automation capability with automatic browser download at install time, but the source does not show secret theft, unrelated exfiltration, self-dependency, or unconsented broad agent-control mutation. The agent path is explicit-user invoked, so the package is suspicious rather than conclusively malicious.
Decision evidence
public snapshot- The postinstall hook runs a shell command to download Chromium automatically.
- The optional orchestrator turns incoming WeChat messages into task files and launches AI CLI harnesses with broad permissions.
- Built-in Codex and Copilot harnesses request full-access or allow-all operation.
- The risky orchestrator path is reached only through the explicit wechat-bro orchestrator command.
- No runtime dependency refers back to this package or creates a nested lifecycle chain.
- Observed network use is for the stated WeChat browser interface and media upload; no unrelated exfiltration endpoint was found.
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@1.6.3.
See all versions of wechat-bro for other recorded verdicts.
- Review the evidence and your use of wechat-bro@1.6.3 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.