ClawHub
Back to skill

Security audit

Wachete

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Wachete connector that discloses its read, write, and delete actions and requires confirmation for state-changing operations.

Before installing, be comfortable routing Wachete actions through OOMOL and the oo CLI. Read-only actions are low risk, but creating, replacing, or deleting monitors should only be approved after checking the exact target and payload.

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 trigger description says to use this skill for ANY Wachete request and instead of calling the API directly, which is overly broad and can cause the agent to invoke the skill for all Wachete-related tasks without sufficient task-specific gating. Because the skill includes write and destructive actions, broad auto-selection increases the chance of unintended state-changing operations being routed through this skill in contexts where a narrower read-only or more specialized path would be safer.

Static analysis

No suspicious patterns detected.