ClawHub
Back to skill

Security audit

Wework

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed WeCom notification helper that can send user-specified messages and files to a WeCom group webhook.

Install only if you intend agents to send messages or selected files to a WeCom group robot. Treat the webhook key as a secret, confirm before sending sensitive files or using @all, and keep usage limited to the intended WeCom endpoint.

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
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill documents use of environment variables and network access to send messages to external WeCom endpoints, but it declares no explicit tool scope or permission boundaries. In an agent environment, this can cause the skill to be invoked with broader-than-necessary capabilities and may enable unintended exfiltration of local file contents or sensitive notifications to an external webhook.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The description uses broad invocation language like 'Use for' across multiple automation and API-development scenarios without stating trigger boundaries, exclusions, or approval requirements. This increases the chance an agent will select the skill in overly broad contexts and perform external messaging actions when the user did not clearly intend notification delivery or file transmission.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.