ClawHub
Back to skill

Security audit

keevx-image-generate

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Keevx image-generation API guide, with expected external uploads for prompts and reference images.

Install only if you are comfortable sending prompts and any reference images to Keevx. Do not use sensitive, private, regulated, or confidential images unless Keevx's terms and data handling are acceptable to you, and use callback URLs only when you trust the destination.

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 (8)

External Transmission

Medium
Category
Data Exfiltration
Content
## API Endpoints

- Base URL: `https://api.keevx.com/v1`
- Upload image: `POST /figure-resource/upload/file` (Content-Type: `multipart/form-data`)
- Create task: `POST /image_generate` (Content-Type: `application/json`)
- Query status: `GET /image_generate/{task_id}`
Confidence
50% 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
## API Endpoints

- Base URL: `https://api.keevx.com/v1`
- Upload image: `POST /figure-resource/upload/file` (Content-Type: `multipart/form-data`)
- Create task: `POST /image_generate` (Content-Type: `application/json`)
- Query status: `GET /image_generate/{task_id}`
Confidence
50% 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
## API Endpoints

- Base URL: `https://api.keevx.com/v1`
- Upload image: `POST /figure-resource/upload/file` (Content-Type: `multipart/form-data`)
- Create task: `POST /image_generate` (Content-Type: `application/json`)
- Query status: `GET /image_generate/{task_id}`
Confidence
50% 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
## API Endpoints

- Base URL: `https://api.keevx.com/v1`
- Upload image: `POST /figure-resource/upload/file` (Content-Type: `multipart/form-data`)
- Create task: `POST /image_generate` (Content-Type: `application/json`)
- Query status: `GET /image_generate/{task_id}`
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill explicitly instructs users to upload local files to a third-party API when a local path is provided, but it does not prominently warn that local images will leave the user's environment and be stored externally. This can lead to unintended disclosure of sensitive local content, especially because users may assume local files are only processed locally.

External Transmission

Medium
Category
Data Exfiltration
Content
### Upload Local File

```bash
curl --location 'https://api.keevx.com/v1/figure-resource/upload/file' \
  --header 'Authorization: Bearer $KEEVX_API_KEY' \
  --header 'source: skill' \
  --form 'file=@"/path/to/local/image.png"'
Confidence
95% confidence
Finding
The upload example shows direct external transmission of a local image file to Keevx. Because the content originates from the local filesystem, the security concern is stronger than generic API usage: it creates a path for accidental disclosure of local data.

External Transmission

Medium
Category
Data Exfiltration
Content
### Upload Local File

```bash
curl --location 'https://api.keevx.com/v1/figure-resource/upload/file' \
  --header 'Authorization: Bearer $KEEVX_API_KEY' \
  --header 'source: skill' \
  --form 'file=@"/path/to/local/image.png"'
Confidence
95% confidence
Finding
The upload example shows direct external transmission of a local image file to Keevx. Because the content originates from the local filesystem, the security concern is stronger than generic API usage: it creates a path for accidental disclosure of local data.

Missing User Warnings

Low
Confidence
86% confidence
Finding
The callback and hosted-image sections describe transmission of generated images and task data through external URLs and third-party storage, but the skill does not clearly frame this as an external data-sharing/privacy consideration. Users may not realize generated assets and callback payloads traverse and reside on external infrastructure for a limited time.

Static analysis

No suspicious patterns detected.