ClawHub
Back to skill

Security audit

copywriting-tone-of-voice-creator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent markdown-based brand voice guide generator with disclosed file-writing and research behavior.

Before installing, expect the skill to read brand context files you provide or keep in the workspace, ask detailed brand/audience questions, use web research for uncovered or regulated categories, and write or modify TONE.md-style markdown files. Review generated guidance for your locale, audience, and regulatory context before using it in production content workflows.

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
  • 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 (1)

Natural-Language Policy Violations

Low
Confidence
87% confidence
Finding
This markdown guidance contains a prescriptive language/locale rule: "Avoid contractions that confuse non-native readers." Under the policy, forcing a particular language style without user opt-in can be a natural-language policy violation unless clearly justified as region-specific; here it is presented as general guidance rather than a documented locale-specific constraint.

Static analysis

No suspicious patterns detected.