ClawHub
Back to skill

Security audit

夸克扫描王 - 转Office Alibaba-Quark-Transoffice

Security checks across malware telemetry and agentic risk

Overview

This skill does what it claims: it sends user-selected images to Quark's document-conversion service and saves the returned Word, Excel, or PDF file locally.

Install only if you are comfortable sending the images or scans you choose to Quark's scan-business.quark.cn service using your SCAN_WEBSERVICE_KEY. Avoid using it for highly sensitive IDs, contracts, medical, financial, or confidential business documents unless that third-party processing is acceptable, and clean up generated files in the temp directory when finished.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill declares environment-variable and network-dependent behavior in metadata and instructions, but the finding indicates those capabilities are not explicitly declared as permissions. This creates a governance gap: the agent may access secrets and transmit user-provided images to a third-party service without a clear permission boundary, reducing reviewability and increasing the chance of unintended data exposure.

Context-Inappropriate Capability

Medium
Confidence
94% confidence
Finding
The save helpers accept a caller-supplied filepath and write to it after only creating parent directories, with no restriction that the destination remain under the skill's temporary workspace. If untrusted or indirectly user-influenced input can reach this parameter, the code can overwrite arbitrary files writable by the process, which exceeds the stated document-conversion purpose and increases tampering risk.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The description says the skill should trigger even when the user did not explicitly ask for format conversion, which broadens invocation beyond clear user intent. In this skill's context, that is risky because invocation sends images to an external server, so overly broad triggering can cause unintended third-party disclosure of sensitive documents.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.