ClawHub
Back to skill

Security audit

Creaa Ai

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Creaa.ai API guide for generating and editing media, with expected third-party data sharing and API-key use but no hidden local execution or persistence.

Before installing, understand that prompts, image URLs, base64 image data, task metadata, and generated results are handled by Creaa.ai and requests may spend API credits. Avoid submitting secrets, regulated data, or sensitive personal/business media unless third-party processing is approved, and protect CREAA_API_KEY like any other credential.

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
93% confidence
Finding
The skill clearly instructs users to send prompts and image/video inputs to the external Creaa API, but it does not warn that potentially sensitive user content will leave the local environment and be processed by a third party. This is a real privacy/security documentation gap because users may unknowingly transmit confidential text, images, or derived media to an external service.

External Transmission

Medium
Category
Data Exfiltration
Content
**Step 1: Submit task**
```bash
curl -s -X POST "https://creaa.ai/api/open/v1/images/generate" \
  -H "Authorization: Bearer $CREAA_API_KEY" \
  -H "Content-Type: application/json" \
  -H "X-Source: openclaw" \
Confidence
96% confidence
Finding
This skill is designed to transmit user-supplied prompts and, in other documented flows, image/video inputs to an external internet service using an Authorization header. In this context the transmission is intentional and core to the feature, but it is still security-relevant because user content and metadata leave the local trust boundary and are exposed to third-party processing and retention risks.

Missing User Warnings

Low
Confidence
84% confidence
Finding
The skill requires an API key via the CREAA_API_KEY environment variable but does not include guidance on protecting that credential or avoiding accidental disclosure in logs, screenshots, or shared shell history. While the examples do not explicitly leak the key, the absence of handling guidance is a legitimate low-severity security weakness in user-facing documentation.

Static analysis

No suspicious patterns detected.