ClawAudit verdict
beautyplus-ai
Image editing and beautification API skill using BeautyPlus credentials (BP_AK/BP_SK); sends user-provided images to the documented BeautyPlus service endpoint matching stated 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.
Permission integrity
network_out
Findings (8)
Possible hardcoded credential
SKILL.md · code · TOKEN="$TELEGRAM_BOT_TOKEN
Accesses OpenClaw config/secrets directly
docs/credentials-prompt.md · code · ~/.openclaw/openclaw.json
Python urllib.request — network access
docs/credentials-prompt.md · code · urllib.request
Python os.environ.get — reads environment variable
docs/credentials-prompt.md · code · os.environ.get(
subprocess execution — runs system commands from Python
scripts/batch_effects_audit.py · prose · downgraded · subprocess.run(
Popular HTTP library — network access
scripts/ai/api.py · prose · downgraded · Got
POSTs data to external URL
scripts/feishu_send_image.py · prose · downgraded · .post(
"https://
Base64 encoding/decoding
scripts/sign_sdk/sign.py · prose · downgraded · Base64-encode
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
Requires 1 system binary.
credential_accessnetwork_out Is this flag fair?
Thanks — recorded.