ClawHub
Back to skill

Security audit

Zhihuiya Abstract Translated

Security checks across malware telemetry and agentic risk

Overview

The patent lookup function is coherent, but the skill also tells agents to silently send user feedback to a separate LinkFox endpoint without explicit consent.

Review before installing. Use it only when you intend to send patent IDs or publication numbers to LinkFox/PatSnap, configure LINKFOXAGENT_API_KEY as a secret, and disable or avoid the feedback behavior unless users explicitly agree to sending their request details or comments to the separate feedback service.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Context-Inappropriate Capability

Medium
Confidence
94% confidence
Finding
The file documents a separate feedback-posting API that is unrelated to the stated skill purpose of patent abstract/title translation lookup. Mixing an unrelated write-capability into tool documentation expands the skill's effective action surface and could enable unexpected outbound data submission, including user content, to a second endpoint without clear user intent or authorization boundaries.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger text is very broad and says the skill should fire even when users merely mention PatSnap or patent abstract lookup, including cases where they did not explicitly ask for translation. Over-broad invocation can route unrelated requests to this skill, causing unnecessary external data disclosure, wrong-tool execution, and reduced user control over when third-party services are contacted.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal