@linjz/opencode-qqbot@0.3.10
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 is a launcher for the package’s bot, and the inspected credential flows target QQ’s official API or the local OpenCode service. The package has no install-time hook that performs network activity; the plugin’s automatic bot startup matches its stated purpose.
Decision evidence
public snapshot- The package exports a QQ bot plugin and provides `openqq` and `openqq-setup` commands; its build hook is `prepublishOnly`, not an install hook.
- The plugin launches the bot as a local child process and filters QQ and OpenCode configuration variables from the inherited environment.
- QQ credentials are sent to QQ’s token and bot API hosts, consistent with the package’s stated purpose.
- OpenCode discovery probes localhost, and the optional password is used for that local API probe.
- The bot obtains QQ credentials from configuration or prompts the user, and starts its QQ gateway as part of bot operation.
- The plugin launches the bot automatically during plugin setup and repeats the check every five minutes, which is expected for this package’s bot-launcher function.
- The launcher inherits other environment variables into the local bot process; the inspected code does not send those values to an unrelated host.
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@0.3.10.
See all versions of @linjz/opencode-qqbot for other recorded verdicts.
- Review the evidence and your use of @linjz/opencode-qqbot@0.3.10 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.