ClawHub
Back to skill

Security audit

Taku Think

Security checks for vulnerabilities and agentic risk

Overview

This skill is a design-planning helper that may read project context and write design notes, and those actions are disclosed and aligned with its purpose.

Before installing, expect this skill to slow down ambiguous build requests so the agent asks clarifying questions and may write or append design documentation in the project. It does not appear to install code, access credentials, or run hidden commands.

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
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger condition goes beyond explicit invocation phrases and includes broad semantic activation such as any request describing a desired end state with unsettled implementation or success criteria. In an agent system, this can cause the skill to activate unexpectedly on many ordinary development conversations, potentially intercepting workflows, steering behavior, or creating denial-of-intent where a more appropriate skill should handle the task.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The markdown instructs the agent to append a ## Design System section to DESIGN.md, which is a file write affecting user project data. The surrounding description does not explicitly warn the user that the skill will modify a file or call for confirmation before doing so.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.