ClawHub
Back to skill

Security audit

Medium

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only writing guidance skill for Medium-style long-form articles, with no code execution, credential access, persistence, or hidden system impact.

Safe to install as a writing-assistance skill. Be aware it may activate for some non-Medium long-form writing requests, so clarify whether you want Medium-oriented deep-read optimization or a simpler rewrite when the context is ambiguous.

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
90% confidence
Finding

The activation rules include broad phrases such as long-form article improvement, deep readability, and improving dense writing without oversimplifying it, which can overlap with many general writing-assistance requests. This can cause the skill to activate outside its intended Medium-specific scope, leading to inappropriate routing, user confusion, or bypass of a better-matched skill, even though it does not directly introduce code-execution or data-exfiltration risk.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.