ClawHub
Back to skill

Security audit

Text Processor

Security checks for vulnerabilities and agentic risk

Overview

This is a simple local text-processing skill with no evidence of hidden access, persistence, network use, or destructive behavior.

This skill appears safe to install for local Chinese or Chinese/English text cleanup and keyword extraction. Users should not rely on it for translation, Markdown/table conversion, or simplified/traditional Chinese conversion unless those capabilities are added or the description is corrected.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding
The implemented code aligns with part of the description: it provides text cleaning/normalization, keyword extraction, and batch processing. However, the description also claims translation and formatting for content production, and no translation logic, external translation service use, or dedicated formatting function is present. The primary purpose is related, but the declared capabilities materially overstate what the code actually does.

Natural-Language Policy Violations

Medium
Confidence
91% confidence
Finding
The file describes the skill as specifically handling Chinese text and Chinese/English mixed text, and the implementation only extracts Chinese keywords. This creates a language/locale restriction in the natural-language description without any user choice or justification that the skill is intentionally region- or language-specific.

Natural-Language Policy Violations

Low
Confidence
82% confidence
Finding
The description and feature list repeatedly frame the skill as operating specifically on Chinese text, including Chinese normalization and Chinese keyword extraction. Because the file does not indicate user choice or opt-in for language/locale constraints, this can be interpreted as a language-specific policy constraint embedded in the skill description.

Static analysis

No suspicious patterns detected.