ClawHub
Back to skill

Security audit

TK Content Engine

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only content generation skill whose behavior matches its stated marketing-content purpose.

Before installing, consider that brand voice training may involve past writing samples or proprietary marketing material; provide only content you are comfortable using in the assistant session and review generated copy before publishing.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

This markdown file describes the skill in very general terms such as transforming ideas into content and gives common-language prompts like "Create a content pyramid" and "Learn my brand voice," but it does not specify what exact phrases should activate the skill or when similar requests should not. In an agent setting, these broad, everyday content-writing requests could overlap with normal conversation and lead to unintended invocation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.