@saltpub/xiaojiu-agent-bridge@0.1.1
Bridge Xiaojiu IM with local CLI coding agents
AI Security Review
scanned 2mo ago · by lpm-firewall-aiNo covert install-time behavior, unrelated endpoint, or concrete credential theft was found. The explicit remote-to-local agent execution and persistence capability is dangerous enough to warn, but the inspected code does not establish malicious intent.
Decision evidence
public snapshot- Webhook messages are passed to a local coding-agent executor.
- The explicit start command installs and starts an OS-managed daemon with automatic restart.
- The bridge sends configured app credentials to the Xiaojiu API to obtain a token.
- The package has no preinstall, install, or postinstall hook.
- Daemon setup is reached only through an explicit CLI start command.
- Message intake applies owner, user, and chat access checks before queuing work.
- Observed network hosts are the named Xiaojiu API and npm registry; no unrelated exfiltration endpoint was found.
Source & flagged code
5 flaggedFindings
Affected versions and remediation
This report applies to @saltpub/xiaojiu-agent-bridge@0.1.1.
See all versions of @saltpub/xiaojiu-agent-bridge for other recorded verdicts.
- Review the evidence and your use of @saltpub/xiaojiu-agent-bridge@0.1.1 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.