Back to skill

Security audit

Content System Humanizer Zh

Security checks for vulnerabilities and agentic risk

Overview

This is a narrowly scoped Chinese text humanizer that reads a user-selected document and writes disclosed local output files.

Install this only if you want a Chinese-language drafting cleanup tool. Be aware it will create or overwrite the documented humanized Markdown and JSON report paths for the chosen slug, and the packaged README appears to reference a missing requirements.txt file.

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
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The file describes the skill entirely in Chinese and explicitly frames it as a Chinese-writing skill, but it does not state whether this language constraint is optional or limited to a justified region-specific use case. Under the policy rule, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The description and title specify that the skill operates on Chinese text only (Chinese text, Humanizer ZH), which imposes a language-specific constraint. The file does not offer a user choice of language or explain a justified region/compliance reason for enforcing this locale, matching the policy category for language or locale constraints without opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The description states the skill will apply a 'constrained Chinese humanization pass,' which imposes a specific language behavior. There is no indication in the manifest that the user can choose the language or that the locale restriction is an explicit opt-in, which can violate language/locale policy requirements.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.