ClawHub
Back to skill

Security audit

Writing Tone Clone

Security checks for vulnerabilities and agentic risk

Overview

This skill is a plain writing-style analysis and skill-generation prompt, with privacy and overwrite cautions users should understand before using personal samples.

Use this only with writing you have the right to analyze and imitate. Redact secrets, financial or medical details, private third-party messages, and identifying details that do not need to be in the sample. Before letting it write files, check whether skills/[name]-voice/SKILL.md or its reference file already exists.

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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly encourages users to provide diaries, journals, personal emails, messages, and voice note transcripts, which are likely to contain sensitive personal data, third-party information, and confidential content. It provides no privacy warning, minimization guidance, redaction instructions, or consent boundaries, making oversharing and downstream misuse of intimate data substantially more likely.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill directs the agent to save generated files into specific workspace paths, but does not warn the user that files will be created and may overwrite existing content or introduce deployable prompt artifacts into the workspace. While the action is expected for a code-generation style skill, the lack of confirmation and safe file-handling guidance can still cause unintended modifications.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.