Caveat verdict
check-bookings-phone
45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.
The skill accesses sensitive information (MIDSCENE_MODEL_API_KEY, MIDSCENE_MODEL_BASE_URL, MIDSCENE_MODEL_NAME) and uses ADB to interact with an Android device.
⚠ 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.
70
security
50
transparency
80
maintenance
Permission integrity
Code accesses API keys/tokens but declares no environment variables
credential_access
Installs packages at runtime — transitive dependencies are not auditable
package_install
Findings (1)
Pattern match medium
Accesses OpenClaw config/secrets directly
SKILL.md · prose · downgraded · ~/.openclaw/openclaw.json
Permissions & capabilities
No declared permissions — minimal attack surface.
package_installcredential_access Is this flag fair?
Thanks — recorded.