ClawHub
Back to skill

Security audit

Tuskr

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Tuskr connector that can read and write Tuskr data through OOMOL, with clear confirmation requirements for state-changing actions.

Install this only if you want agents to operate your Tuskr workspace through OOMOL. Reads may run directly, while creates and result updates should be checked carefully because they change Tuskr data; review any requested oo CLI installation or login step before proceeding.

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
91% confidence
Finding
The skill description says to use this skill for ANY Tuskr request and whenever a task involves Tuskr, which creates an overly broad routing trigger. This can cause the agent to invoke the skill for loosely related mentions of Tuskr, increasing the chance of unnecessary external actions, schema probing, or unintended reads/writes in a connected third-party system.

Static analysis

No suspicious patterns detected.