ClawAudit verdict
evez-oracle-bridge
The skill routes LLM calls through a Vultr oracle instance.
⚠ 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 (4)
Possible hardcoded credential
evez_telegram_bridge.py · prose · downgraded · API_KEY = "EVEZ_API_KEY_REDACTED
HTTP request to bare IP address — common in malicious payloads
evez_telegram_bridge.py · prose · downgraded · http://127.0.0.0
Python os.environ.get — reads environment variable
evez_telegram_bridge.py · prose · downgraded · os.environ.get(
Python aiohttp session — async network access
evez_telegram_bridge.py · prose · downgraded · aiohttp.ClientSession
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.