ClawHub
Back to skill

Security audit

Brand Guidelines

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple brand-style reference for applying Anthropic-like colors and typography, with no executable behavior or privileged access.

Install this if you want an agent to apply Anthropic-style visual branding. Be aware that its trigger wording is broad, so users should invoke it intentionally for Anthropic branding or official brand-style work rather than generic formatting 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 (2)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The description says the skill applies to 'any sort of artifact that may benefit' from the brand look-and-feel, which is extremely broad and can cause the agent to invoke this skill for many unrelated formatting tasks. Overbroad activation increases unnecessary tool/skill usage, can override user intent, and may create opportunities for prompt-scope confusion across otherwise generic requests.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The overview instructs agents to use the skill to access brand identity resources without defining clear invocation boundaries. This ambiguity can cause the skill to be selected whenever a request vaguely relates to design or formatting, leading to unintended behavior and excessive application of brand-specific transformations.

Static analysis

No suspicious patterns detected.