ClawAudit verdict
daily-maoxuan-push
Daily quote push skill using DeepSeek API and Telegram bot to send quotes with AI analysis; credentials are from env vars, the Publisher Note explicitly documents prior security issues as resolved, and all behavior matches the stated daily-push purpose.
⚠ 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 (5)
Possible hardcoded credential
SKILL.md · code · TOKEN="your-bot-token
Python os.environ.get — reads environment variable
scripts/deep_gen.py · prose · downgraded · os.environ.get(
Python httpx request — network access
scripts/deep_gen.py · prose · downgraded · httpx.post(
pip3 install — installs Python packages at runtime
scripts/install.sh · prose · downgraded · pip3 install
Python urllib.request — network access
scripts/push_daily.py · prose · downgraded · urllib.request
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.