ClawHub
Back to skill

Security audit

brand-guidelines

Security checks for vulnerabilities and agentic risk

Overview

This is a low-risk brand styling skill that only provides colors, fonts, and formatting guidance, with no code execution or sensitive access.

Install this only if you want agents to apply Anthropic-style branding to artifacts. Be aware it may steer generic styling requests toward Anthropic colors and fonts unless the user or agent scopes its use clearly.

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
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill description is overly broad: phrases like applying brand styling to 'any sort of artifact' and invoking it whenever brand colors or style guidelines 'apply' can match many ordinary formatting requests. This can cause the agent to activate the skill in contexts where the user did not specifically request Anthropic branding, leading to unintended scope expansion, output modification, or interference with more appropriate skills.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.