ClawHub
Back to skill

Security audit

Voice AI Agent Engineering

Security checks for vulnerabilities and agentic risk

Overview

This is a non-executable voice AI design playbook; users should treat its AI-disclosure guidance cautiously but it does not show malicious or hidden behavior.

Install only if you want a voice-agent design playbook. Before using its templates in production, change the default disclosure rule to match your company policy and applicable AI disclosure, call recording, TCPA, GDPR, PCI, HIPAA, and state-law requirements.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill explicitly recommends 'Never say "I'm an AI" unprompted' except when required by law, which normalizes non-disclosure by default in a voice system interacting with users. This can create legal/compliance exposure in jurisdictions requiring AI disclosure and can mislead callers about the nature of the interaction, especially in sensitive customer service or sales contexts.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 264)May include surrounding context.

NEVER:

  • Provide medical/legal/financial advice
  • Share other patients' information
  • Make promises about pricing without checking
  • Continue if caller says "stop" or "goodbye"
text

Static analysis

No suspicious patterns detected.