Back to skill

Security audit

Brand Voice Extractor

Security checks for vulnerabilities and agentic risk

Overview

This is a content-writing helper that asks for writing samples or questionnaire answers and produces a reusable brand voice profile, with no hidden code or privileged behavior found.

Before installing, expect to provide representative writing samples or answer brand-positioning questions. Avoid pasting confidential content unless you are comfortable using it to create a reusable voice profile, and decide where any saved profile should live.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The README tells users to invoke the skill with phrases like "Run brand-voice-extractor in Extract mode" or "Build mode," but it does not define the exact accepted triggers, scope, or any negative examples. In a markdown skill description, this ambiguity can cause unintended or inconsistent activation, especially because "Build mode" alone is very generic.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

Line L023 says the voice "learned to explain things in English," which presents English as the required output style. In a sample output for a skill, this is a natural-language locale constraint, and the file does not indicate that users can choose another language or that English is required for a documented regional reason.

Content

No source excerpt is available for this finding.