wechat-bro@1.5.0
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 dangerous AI-agent messaging capability with local configuration mutation and deceptive default behavior, so it warrants a warning. Source inspection did not establish malware, automatic foreign agent-control takeover, credential theft, or a lifecycle self-dependency chain.
Static reason
High-risk behavior combination matched malicious policy.; source matched previously finalized malicious package; routed for review; previous stored version diff introduced dangerous source
Trigger
The user starts the daemon and then runs wechat-bro orchestrator.
Impact
Can autonomously act through the logged-in WeChat account and misrepresent the sender as human.
Mechanism
Message-triggered AI-agent dispatch, local agent configuration mutation, and automated WeChat replies.
AI rationale
This is a dangerous AI-agent messaging capability with local configuration mutation and deceptive default behavior, so it warrants a warning. Source inspection did not establish malware, automatic foreign agent-control takeover, credential theft, or a lifecycle self-dependency chain.
Evidence
src/cli.jssrc/orchestrator.jsskills/wechat-bro/agents/wechat-individual-maintainer.mdpackage.json~/.wechat-bro/contacts/<contact>/AGENTS.md~/.wechat-bro/contacts/<contact>/.task-<timestamp>.md
Network endpoints1
wx.qq.com
Decision evidence
public snapshotAI called this Suspicious at 88.0% confidence as Dangerous Capability with low false-positive risk.
Evidence for warning
- The install hook automatically runs an npx browser-install command.
- The optional orchestrator overwrites or creates AGENTS.md and launches an npx AI harness through a shell for incoming watched messages.
- Bundled agent instructions direct automated replies that conceal the AI identity and impersonate the account holder.
Evidence against
- The orchestrator is activated only by the explicit wechat-bro orchestrator command.
- No self-dependency, secret harvesting, remote payload loader, or non-WeChat exfiltration was found.
- The install hook targets the package's Chromium cache rather than an AI-agent control surface.
Behavioral surface
ChildProcessEnvironmentVarsFilesystemNetworkWebSocket
HighEntropyStringsUrlStrings
Source & flagged code
8 flaggedpackage.jsonView file
•scripts.postinstall = node -e "const p=require('path'),o=require('os'),d=p.join(o.homedir(),'.wechat-bro','chromium');process.env.PUPPETEER_CACHE_DIR=d;const pup=require('puppeteer');(async()=>{try{awai...
Critical
Red Install Lifecycle Script
Install-time lifecycle script matches a deterministic static-gate block pattern.
package.jsonView on unpkg•scripts.postinstall = node -e "const p=require('path'),o=require('os'),d=p.join(o.homedir(),'.wechat-bro','chromium');process.env.PUPPETEER_CACHE_DIR=d;const pup=require('puppeteer');(async()=>{try{awai...
High
Install Time Lifecycle Scripts
Package defines install-time lifecycle scripts.
package.jsonView on unpkg•stage = ast_semantic_analysis; reason = ast_parse_error; limitedFiles = 1
High
Semantic Analysis Limited
A bounded semantic-analysis stage reached its safety limit; remaining detectors completed, but this package requires AI review.
package.jsonView on unpkgFindings
2 Critical6 High3 Medium4 Low
CriticalRed Install Lifecycle Scriptpackage.json
CriticalPrevious Version Dangerous Deltasrc/cli.js
HighInstall Time Lifecycle Scriptspackage.json
HighChild Processsrc/upload.js
HighSame File Env Network Executionsrc/cli.js
HighRuntime Package Installsrc/cli.js
HighSemantic Analysis Limitedpackage.json
HighKnown Malware Source Similaritypackage.json
MediumNetwork
MediumEnvironment Vars
MediumStructural Risk Force Deep Review
LowScripts Present
LowFilesystem
LowHigh Entropy Strings
Affected versions and remediation
This report applies to wechat-bro@1.5.0.
See all versions of wechat-bro for other recorded verdicts.
- Review the evidence and your use of wechat-bro@1.5.0 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.