Caveat verdict
email-customer-assistant
IMAP email reading + AI classification + Feishu push skill that explicitly states it is read-only, requires user confirmation before any action, and does not touch platform APIs; no exfiltration or suspicious behavior.
⚠ 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 (4)
Possible hardcoded credential
README.md · code · password: "your_app_password
Python urllib.request — network access
scripts/check_emails.py · prose · downgraded · urllib.request
Python os.environ.get — reads environment variable
scripts/check_emails.py · prose · downgraded · os.environ.get(
References webhook/callback URL
scripts/feishu_pusher.py · prose · downgraded · webhook_url
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.