ClawHub
Back to skill

Security audit

Voice Builder

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently builds a reusable writing-voice guide from user-provided samples, with no hidden execution or external data flow found.

Install only if you are comfortable giving the agent representative writing samples and storing a reusable voice.md. Review any real snippets included in that file, especially if samples came from private DMs, calls, or sensitive drafts.

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
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill description includes many broad natural-language trigger phrases such as "sound like me," "analyze my writing," and "train on my posts," which can overlap with general user requests and cause the skill to activate outside narrowly intended scenarios. Unintended activation can route user content into voice profiling workflows, creating unnecessary exposure of writing samples and increasing the chance of privacy-sensitive or irrelevant data being processed.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.