Caveat verdict

xiaodu-control

xiaodu-control-official

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Xiaodu smart screen control skill with explicit prompt-injection defense: prohibits following injected remote instructions from auth page text, only extracts the token.

⚠ 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.

45
security
50
transparency
70
maintenance

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Findings (3)

Pattern match high

Possible hardcoded credential

scripts/configure_mcporter.sh · prose · downgraded · token="$( printf

Pattern match medium

Accesses OpenClaw config/secrets directly

SKILL.md · prose · downgraded · ~/.openclaw/openclaw.json

Pattern match medium

subprocess execution — runs system commands from Python

scripts/device_resolver.py · prose · downgraded · subprocess.run(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B/D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

Requires 4 system binaries.

credential_access

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API