@saltpub/xiaojiu-agent-bridge@0.1.3
Bridge Xiaojiu IM with local CLI coding agents
AI Security Review
scanned 21d ago · by lpm-firewall-aiThe manifest’s lifecycle scripts perform build and typecheck tasks. The flagged process, network, telemetry, and Claude-history behavior is consistent with the bridge’s CLI and user-invoked resume flow; no concrete attack behavior was found.
Decision evidence
public snapshot- package.json maps the CLI executable to its bin file; its prepare and prepublishOnly scripts run build and typecheck tasks.
- The CLI sends the app secret to the default Xiaojiu messenger API token endpoint.
- Claude session history is read for the /resume command; history previews are withheld in group chats and returned through the bridge chat.
- The optional telemetry module is imported only when its environment variable is set.
Source & flagged code
5 flaggedThis package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
dist/cli.jsView on unpkgFindings
Affected versions and remediation
This report applies to @saltpub/xiaojiu-agent-bridge@0.1.3.
See all versions of @saltpub/xiaojiu-agent-bridge for other recorded verdicts.
- Review the evidence and your use of @saltpub/xiaojiu-agent-bridge@0.1.3 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.