ClawHub
Back to skill

Security audit

Model

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown guidance skill about using AI models, with no scripts, persistence, credential handling, or hidden tool behavior.

This skill appears safe to install as general AI-model guidance. Its main limitation is broad scope: install it if you want frequent help with model choice, prompting, evaluation, and AI workflows, and consider narrowing its description if you only want it invoked for specific model-selection tasks.

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
89% confidence
Finding
This markdown file is in scope for vague-trigger review. The description frames the skill as applicable to essentially any AI-model-related need, but does not specify concrete invocation conditions, exclusions, or examples of when the skill should not activate, which increases the chance of unintended invocation overlap with many ordinary AI-help requests.

Static analysis

No suspicious patterns detected.