ClawHub
Back to skill

Security audit

Dianping-query

Security checks across malware telemetry and agentic risk

Overview

The skill is aligned with looking up Dianping restaurant information, but it directs use of a named logged-in account without clear ownership or consent controls.

Review before installing. The restaurant lookup behavior is coherent, but the skill should ideally use public Dianping pages by default and ask before using any logged-in session, especially a named account that may not belong to the current user.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The skill description is broad enough to trigger on many generic restaurant- or recommendation-related requests without clear boundaries. Over-broad routing can cause the agent to invoke this skill in unintended contexts, leading to unnecessary browsing, use of a logged-in account, and possible mishandling of user intent or site-specific actions.

Natural-Language Policy Violations

Medium
Confidence
84% confidence
Finding
The skill content is written to operate in Chinese and does not offer a user language choice, which can cause incorrect execution or misleading outputs for users interacting in other languages. While not a direct exploit primitive, this can degrade consent and accuracy, especially when the skill performs browsing steps on behalf of a user using a logged-in session.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.