ClawHub
Back to skill

Security audit

ToyBridge

Security checks for vulnerabilities and agentic risk

Overview

The skill clearly controls a local BLE toy bridge, but it needs review because it can activate an intimate physical device at high intensity without explicit safety or consent gates.

Install only if you trust the local ToyBridge setup and are comfortable with an agent sending live device-control commands. Before use, require explicit confirmation for each session, verify the correct device and environment, start at low intensity, and keep the stop command available.

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 (3)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill provides direct commands to activate a physical intimate device, including strong and maximum intensity presets and automated patterns, but omits explicit consent, bodily safety, emergency stop, and unintended activation warnings. Because the agent is instructed to issue live control commands via curl, misuse or accidental triggering could cause non-consensual activation, injury, distress, or unsafe operation in a sensitive physical context.

External Transmission

Medium
Category
Data Exfiltration
Content
### Vibrate at intensity

```bash
curl -s -X POST http://host.docker.internal:8888/vibrate \
  -H "Content-Type: application/json" \
  -d '{"intensity": 60}'
```
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
### Vibrate at intensity

```bash
curl -s -X POST http://host.docker.internal:8888/vibrate \
  -H "Content-Type: application/json" \
  -d '{"intensity": 60}'
```
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Static analysis

No suspicious patterns detected.