ClawHub
Back to skill

Security audit

medium-posts

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Medium publishing guidance skill with no executable code, network calls, persistence, or hidden data movement.

Install this if you want Medium-specific publishing and optimization guidance. Be aware it may read existing `.claude` or `.cursor` project context files for keyword and content strategy sections when present, but the artifact does not execute code or send data anywhere.

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
Confidence
94% confidence
Finding
The trigger description is broad enough that ordinary requests about writing, publishing, or optimizing posts could activate this skill even when the user does not specifically want Medium-focused guidance. That can cause incorrect skill routing and platform-specific SEO advice to be applied in the wrong context, leading to misaligned actions or recommendations.

Static analysis

No suspicious patterns detected.