ClawHub
Back to skill

Security audit

sag

Security checks for vulnerabilities and agentic risk

Overview

The scanners report a benign verdict with no AIG findings, while noting that voice generation may send reply text to ElevenLabs without a clear privacy disclosure.

Before installing, consider whether you may use voice generation with private or sensitive text. Skillspector recommends disclosing that text is sent to ElevenLabs and getting confirmation before sending sensitive content. The scan was partial because a local path-like reference could not be resolved, so the evidence is incomplete.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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)

Voice generation sends reply text to ElevenLabs without a privacy disclosure.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The workflow instructs the agent to synthesize reply text using ElevenLabs, but never warns that this text is transmitted to a third-party service. Naming ElevenLabs and describing local playback does not clearly disclose that potentially sensitive conversation content leaves the user's system.

Content

No source excerpt is available for this finding.