ClawHub
Back to skill

Security audit

Content Headline Generator

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only headline-writing skill with no code execution or data access; users should simply review generated marketing claims for accuracy.

Installers should understand this skill is mainly aimed at headline/copywriting workflows and uses persuasive marketing patterns. Review generated titles for factual support, platform policy compliance, and whether claims are too exaggerated for the underlying content.

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)

Natural-Language Policy Violations

Medium
Confidence
96% confidence
Finding
The file's instructional content, examples, and usage guidance are all presented in Chinese, and there is no indication that users may choose another language or that the skill is intentionally limited to Chinese-speaking users. Under the policy provided, forcing a specific language without user opt-in is a natural-language policy violation.

Vague Triggers

Low
Confidence
82% confidence
Finding
The README tells users to provide more context and marks `只说"帮我写个标题"` as insufficient, but the document does not clearly define the actual invocation scope or a bounded set of trigger phrases. Because the skill is described in natural language rather than with specific activation constraints, common phrases about writing a title could still ambiguously overlap with ordinary conversation.

Static analysis

No suspicious patterns detected.