ClawHub
Back to skill

Security audit

brand-voice

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed brand-voice helper that changes writing style and stores simple profile/event notes, with no executable code or hidden behavior found.

Before installing, understand that this skill may influence tone across supported writing workflows and may create or use workspace-local brand profile and voice event files. Use explicit `--voice` choices when possible if you want to avoid accidental tone changes from broad style-related prompts.

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
Confidence
96% confidence
Finding
The trigger keywords are generic terms such as 'brand voice', 'writing style', and 'speaking style', which can overlap with ordinary user requests and cause the skill to activate unintentionally. In this skill’s context, unintended invocation could alter output style, write to related profile/event paths through integrations, or interfere with other writing workflows, though it does not by itself introduce direct code execution or privilege escalation.

Static analysis

No suspicious patterns detected.