ClawHub
Back to skill

Security audit

Chuhaijiang

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed read-oriented Chuhaijiang connector wrapper with proportionate account access and no hidden persistence or destructive behavior.

Before installing, be comfortable using the OOMOL oo CLI and connecting your Chuhaijiang account. Let the agent run read/search Chuhaijiang actions directly, but review any future connector action marked write or destructive before approving it.

SkillSpector

Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The description instructs the agent to use this skill for "ANY Chuhaijiang request" and "instead of calling the API directly," which is an overly broad activation rule. This can cause the skill to be invoked in situations where a narrower or safer path would be more appropriate, increasing the chance of unintended tool use, data exposure through connector calls, or bypass of more context-specific safeguards.

Static analysis

No suspicious patterns detected.