ClawHub
Back to skill

Security audit

WeCom Bot

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a transparent WeCom Bot connector, but its first-time setup tells an agent to install the OOMOL CLI by executing a remote script directly in the shell.

Review the setup section before installing. Prefer installing the oo CLI from official documentation with a pinned or verifiable release, and require explicit approval before any write, delete, message-send, or dynamic call_tool action against your WeCom workspace.

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
98% confidence
Finding

The skill instructs use of a remote installation command that pipes a downloaded script directly into a shell (curl ... | bash). This is dangerous because it executes unverified code from the network immediately; if the host, CDN, DNS, TLS trust chain, or distribution endpoint is compromised, arbitrary code can run on the user's machine.

Content

Scanner excerpt · SKILL.md (reported line 108)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The description instructs the agent to use this skill for "ANY WeCom Bot request" and instead of calling the API directly, which creates an overly broad auto-invocation surface. Broad trigger wording can cause the skill to be selected in unintended contexts, increasing the chance that high-risk write or destructive actions are exposed when the user only intended a narrower WeCom-related task.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.