Back to skill

Security audit

Branding

Security checks for vulnerabilities and agentic risk

Overview

This is a low-risk branding guidance skill that provides brand identity, color, typography, and voice advice without hidden execution or sensitive access.

This skill is reasonable to install for brand strategy and style-guide work. Be aware that its invocation wording is broad, so it may appear for general product look-and-feel requests, but the inspected content does not perform actions, access private data, or install anything.

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
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
95% confidence
Finding

The manifest description lists many specific brand-related phrases, but then expands scope to "or any task related to defining how a product looks, feels, and sounds." That catch-all is ambiguous and could overlap with many general product, marketing, UX, or content requests, making unintended invocation more likely.

Content

No source excerpt is available for this finding.