ClawHub
Back to skill

Security audit

WPS MCP

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent for WPS document automation, but its setup instructions include unverified remote installer execution that users should review before installing.

Review the oo CLI installer source or use an official, verifiable installation method before following the setup commands. Only connect a WPS account whose documents you are comfortable letting this connector read or modify, and require explicit confirmation before any write or destructive action.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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)

External Script Fetching

High
Category
Supply Chain
Confidence
96% confidence
Finding

The skill includes a curl ... | bash installation command that fetches and immediately executes remote code without integrity verification, pinning, or user-side review. If the install endpoint, transport path, or upstream distribution is compromised, users could execute arbitrary code on their system, making this especially dangerous in a skill document that may be followed operationally.

Content

Scanner excerpt · SKILL.md (reported line 63)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description says to use this skill for "ANY WPS MCP request," which is overly broad routing language and can cause the agent to invoke this skill in situations where a narrower or safer path would be more appropriate. In a connector skill that supports both read and state-changing actions, unintended activation increases the chance of unnecessary data exposure or accidental writes if downstream prompts or user intent are ambiguous.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.