ClawHub
Back to skill

Security audit

Literary Essay Writer 1

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese literary essay writing guide with no code execution, data access, persistence, or hidden privileges.

Install this only if you want a Chinese literary essay/book-review writing style to shape responses. For non-Chinese or general-purpose writing, invoke a different skill or explicitly state your preferred language and format.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
94% confidence
Finding

The skill description defines broad trigger scenarios such as book reviews, reading reflections, and life-philosophy public-account writing, which can match a wide range of generic writing requests. This increases the chance the skill is invoked outside a narrowly intended context, causing instruction overreach and unintended steering of user tasks.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill is written entirely in Chinese and frames outputs around Chinese-language公众号 writing without giving the user a language-choice mechanism. This can improperly override user language preferences or cause the skill to be selected for requests where the user expects another language, reducing reliability and potentially causing policy or UX mismatches.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.