ClawHub
Back to skill

Security audit

内容写作优化技能

Security checks for vulnerabilities and agentic risk

Overview

This is a small writing-advice skill with no code, network access, persistence, or sensitive data handling.

Installers should treat this as a low-risk writing style helper. Its broad description may make it appear during many editing tasks, so users who want narrower behavior should prefer a version with clearer trigger examples and boundaries.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The description "Fix AI writing patterns that create repetitive and robotic content" states the purpose broadly but does not define specific trigger phrases, scope boundaries, or exclusion conditions. In a manifest-style file, this can make invocation criteria ambiguous for general writing-assistance requests.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.