Caveat verdict
whatsapp-monitor
WhatsApp keyword monitoring skill that aggregates matched messages to a user-configured Feishu table; all monitoring targets and export destinations are user-configured and match the stated monitoring purpose.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (5)
Possible hardcoded credential
references/openclaw_whatsapp_integration.md · prose · downgraded · token: "YOUR_ACCESS_TOKEN
HTTP request to bare IP address — common in malicious payloads
references/port_configuration.md · code · http://192.168.1.100
References sudo — requests elevated privileges
references/port_configuration.md · code · sudo
Python os.environ.get — reads environment variable
references/port_configuration.md · code · os.environ.get(
Python aiohttp session — async network access
references/port_configuration.md · code · aiohttp.ClientSession
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class C). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.