Caveat verdict
qqbot
QQ official bot configuration guide that walks through standard bot registration, IP whitelist setup, and OpenClaw integration using documented platform APIs; no malicious behavior or exfiltration present.
⚠ 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.
Permission integrity
network_out
package_install
Findings (6)
Possible hardcoded credential
SKILL.md · code · SECRET = "你的AppSecret
Pipe to python — executes piped content as Python code
qq_ai_handler.sh · prose · downgraded · | python3
Opens WebSocket connection
CLAWHUB_PUBLISH.txt · code · WebSocket
pip3 install — installs Python packages at runtime
SKILL.md · code · pip3 install
setuid — privilege escalation mechanism
clawhub-publish.js · prose · downgraded · setuid
Python aiohttp session — async network access
qq_official_bot.py · prose · downgraded · aiohttp.ClientSession
Permissions & capabilities
No declared permissions — minimal attack surface.
network_outpackage_install Is this flag fair?
Thanks — recorded.