ClawAudit verdict
zalo-agent
Wraps a user-installed CLI tool (zalo-agent) for Zalo messaging automation; all commands are documented CLI invocations consistent with the stated messaging/OA automation purpose, with no exfiltration or hidden behavior.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (3)
Opens WebSocket connection
references/mcp-guide.md · code · WebSocket
References tunneling service
references/oa-command-reference.md · code · ngrok
References webhook/callback URL
references/oa-command-reference.md · prose · downgraded · webhookUrl
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class F). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
Requires 1 system binary.
network_in Is this flag fair?
Thanks — recorded.