ClawAudit verdict
ai-search-hub
The skill is designed for automating browser interactions with specific AI search sites and does not show any malicious intent.
⚠ 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 (7)
HTTP request to bare IP address — common in malicious payloads
SKILL.md · prose · downgraded · http://127.0.0.1
Long base64 string (100+ chars) — likely obfuscated payload
README.en.md · prose · downgraded · PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHZpZXdCb3g9IjAgMCAyNCAyNCI+
subprocess execution — runs system commands from Python
scripts/run_web_chat.py · prose · downgraded · subprocess.run(
Python urllib.request — network access
scripts/doubao_playwright.py · prose · downgraded · urllib.request
Opens WebSocket connection
scripts/run_web_chat.py · prose · downgraded · WebSocket
Python os.environ.get — reads environment variable
scripts/run_web_chat.py · prose · downgraded · os.environ.get(
Python shutil file operation — copies/moves/deletes files
scripts/run_web_chat.py · prose · downgraded · shutil.rmtree(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D). 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.