ClawHub
Back to skill

Security audit

Brand Guidelines Anthropic

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple brand-styling guide with no executable code, persistence, credential access, or data movement.

This appears safe to install from a security standpoint. Before relying on it for public Anthropic-branded materials, verify the colors and typography against an authoritative brand source, and be aware it may activate for broad visual-formatting requests unless the trigger text is narrowed.

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
86% confidence
Finding
The description says to use the skill for "any sort of artifact that may benefit" from Anthropic's look-and-feel and whenever "visual formatting" or "design standards" apply. This is very broad and lacks clear boundaries or exclusion cases, which could cause the skill to match many ordinary formatting requests unintentionally.

Static analysis

No suspicious patterns detected.