ClawHub
Back to skill

Security audit

social-media-viral-title-generator

Security checks for vulnerabilities and agentic risk

Overview

This is a simple title-writing skill with no code execution, data access, persistence, or hidden high-impact behavior.

This skill appears safe to install for drafting social-media titles. Users should be aware that generic trigger names may activate it for some unrelated title-writing requests, so narrower trigger names would make it easier to control.

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 (3)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger list includes generic commands such as /generate-title, /post-title, and /title-optimize that are broad enough to match common user intents outside this specific skill. In an agent ecosystem with multiple skills, this can cause unintended invocation, skill shadowing, or routing hijacks where a generic request is captured by this marketing-focused skill instead of a more appropriate one.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger keyword '/post-title' is ambiguous because 'post' and 'title' are broadly applicable across blogging, forums, CMS tools, and general writing workflows, not just viral social-media content. This increases the chance of accidental invocation and skill hijacking of unrelated user intents, which can produce incorrect outputs or interfere with safer, more appropriate skills.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger keyword '/generate-title' is overly generic and can match many unrelated agent requests about title generation, causing this skill to activate outside its intended social-media viral-title scope. In a multi-skill environment, that ambiguity can lead to prompt routing collisions, unintended execution, and reduced trust in agent behavior, especially when broader title-writing requests contain sensitive or context-specific content.

Static analysis

No suspicious patterns detected.