ClawHub
Back to skill

Security audit

Whisper Tailnet API

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple guide for sending audio to a disclosed Tailnet Whisper service, but users should treat any uploaded audio as shared with that service.

Install only if you intend to send audio files to this shared Tailnet Whisper server. Avoid confidential, regulated, or consent-sensitive recordings unless you trust the server operator, network path, and retention practices.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Confidence
96% confidence
Finding
The skill instructs agents to send audio data to a remote transcription service over plain HTTP and does not warn about privacy, consent, or data handling. Audio content may contain sensitive personal or business information, and transmitting it to a shared remote host without disclosure increases the risk of unauthorized disclosure and misuse.

External Transmission

Medium
Category
Data Exfiltration
Content
## Quick health check

```bash
curl -sS http://100.92.116.99:8765/health
```

## Transcribe audio (recommended)
Confidence
87% confidence
Finding
The skill directs use of an external network endpoint and encourages uploading raw audio content to it. In context, this is the core function of the skill, but it still creates a real data exfiltration pathway—especially because the endpoint uses HTTP to a remote Tailnet address and the guidance lacks trust, authentication, or sensitivity constraints.

Static analysis

No suspicious patterns detected.