ClawHub
Back to skill

Security audit

Geepers Llm

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward instruction-only skill for sending user-selected LLM requests to a disclosed third-party API.

Install only if you trust dr.eamer.dev and its provider routing. Use a dedicated, revocable API key, and avoid sending secrets, regulated data, confidential business content, private images, or personal information unless you are comfortable with that third-party processing.

SkillSpector

By NVIDIA
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 (5)

Missing User Warnings

Medium
Confidence
98% confidence
Finding
The skill explicitly instructs users to send prompts, images, and text to a third-party API, but the description does not warn that user content and metadata will leave the local environment and be processed by an external service. This creates a real privacy and compliance risk because users may unknowingly transmit sensitive prompts, media, or proprietary data to an intermediary endpoint and potentially onward to multiple model providers.

External Transmission

Medium
Category
Data Exfiltration
Content
### Chat Completion
```
POST https://api.dr.eamer.dev/v1/llm/chat
Headers: X-API-Key: $DREAMER_API_KEY
Body:
{
Confidence
97% confidence
Finding
This endpoint sends chat contents and an API key to an external third-party service, which is a genuine external transmission risk in a skill context. Because the service is described as brokering access across multiple providers, prompts may be exposed beyond the immediate user environment and potentially shared with downstream vendors, increasing privacy, confidentiality, and compliance exposure.

External Transmission

Medium
Category
Data Exfiltration
Content
### Vision (image analysis)
```
POST https://api.dr.eamer.dev/v1/llm/vision
Body: { "model": "claude-sonnet-4-5-20250929", "image_url": "...", "prompt": "Describe this image" }
```
Confidence
98% confidence
Finding
The vision endpoint transmits image references and prompts to an external third-party API for analysis, which can expose sensitive images, embedded personal data, or confidential visual information. In this skill's context, the danger is elevated because users may assume they are only using an LLM feature, while the content may also be routed through an intermediary and possibly downstream providers.

External Transmission

Medium
Category
Data Exfiltration
Content
### Image Generation
```
POST https://api.dr.eamer.dev/v1/llm/image
Body: { "prompt": "A sunset over the ocean", "provider": "openai" }
```
Confidence
90% confidence
Finding
The image-generation endpoint sends user prompts to an external service, which is a real data-transmission issue because prompts may contain confidential project details, personal information, or other sensitive context. Although no local code execution is implied, the lack of disclosure can cause unintentional sharing of proprietary information with third parties.

External Transmission

Medium
Category
Data Exfiltration
Content
### Text-to-Speech
```
POST https://api.dr.eamer.dev/v1/llm/tts
Body: { "text": "Hello world", "voice": "alloy" }
```
Confidence
95% confidence
Finding
The text-to-speech endpoint sends raw text to an external API, which can expose sensitive written content, credentials, customer information, or internal material if users are not warned. Because the skill encourages use as a convenience wrapper, users may underestimate that their text leaves the system and is processed by a third party.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.