Back to skill

Security audit

Brand Voice Style Guide

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only marketing prompt skill that generates brand voice style guides without code execution, credentials, persistence, or hidden system changes.

Reasonable to install if you want help creating brand voice documentation. Review generated rules for your own language, region, and audience, and avoid pasting confidential unreleased copy unless you are comfortable having the agent process it.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The style guide hard-codes language constraints such as 'Never uses slang' and 'always explains it' in a single brand voice with no option for alternate languages or locales. Because this markdown file is natural-language guidance intended to govern outputs, the absence of any user choice or documented regional justification creates a language/locale policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The guide requires specific English-language conventions including Oxford comma usage, sentence case headers, and a U.S. date format ('Month DD, YYYY'). These are locale-specific rules presented as mandatory for all outputs, with no user opt-in or region-specific justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.