ClawHub
Back to skill

Security audit

tcms-writer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed marketing-writing assistant that reads scoped source material and writes draft files for human review, with no evidence of hidden execution or persistence.

Installers should use this for product-marketing long-form drafts only, provide a clear brief and target product, and review generated files before use, especially when internal customer or unpublished product information is involved.

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
Confidence
95% confidence
Finding
The skill registers on very broad everyday Chinese triggers such as 写文章/写稿/起草, which are not narrowly scoped to this skill’s specific purpose. This can cause unintended activation for general writing requests, leading the agent to apply brand-marketing workflow, file reads, and drafting behavior in contexts the user did not intend.

Vague Triggers

Low
Confidence
89% confidence
Finding
Generic English triggers like content brief, draft, and 按brief写 are too broad and may match many unrelated authoring tasks. In an environment with tool access to read and write files, overbroad activation increases the chance of the wrong skill taking control and producing inappropriate outputs or accessing unnecessary project materials.

Static analysis

No suspicious patterns detected.