@linjz/opencode-qqbot@0.3.4
QQ Bot for OpenCode AI - chat with AI coding assistant via QQ
AI Security Review
scanned 2d ago · by lpm-firewall-aiThe flagged process execution launches the package’s own bot, while the reviewed credentials go to QQ’s official API or to loopback OpenCode endpoints. Setup writes QQ credentials only after an explicit QR binding command; no unrelated collection or unsolicited account action was identified.
Decision evidence
public snapshot- The package exports a plugin and exposes CLI commands; its prepublishOnly script builds bundles and is not an install hook.
- The CLI selects the package’s TypeScript entry or its bundled bot for an explicit command invocation.
- The plugin checks for configured QQ credentials before launching the bot.
- OpenCode discovery sends the optional password only to loopback addresses and disables redirects.
- QQ app credentials are used with QQ’s official token and API endpoints.
- The setup command obtains credentials through a user-started QR binding flow and writes them to ~/.openqq/.env.
- The package runs a detached bot and performs network requests as part of its bot purpose.
- The bundled bot reads OPENCODE_PASSWORD and probes local OpenCode endpoints during startup recovery.
Source & flagged code
5 flaggedSource spawns a local helper that also contains network and dynamic execution context; review data flow before blocking.
bin/openqq.jsView on unpkg · L6Findings
Affected versions and remediation
This report applies to @linjz/opencode-qqbot@0.3.4.
See all versions of @linjz/opencode-qqbot for other recorded verdicts.
- Review the evidence and your use of @linjz/opencode-qqbot@0.3.4 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.