ClawHub
Back to skill

Security audit

AI Icon Generator

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward API-backed icon generator, with the main caution that prompts and generated assets go to a third-party service.

Install only if you are comfortable sending icon descriptions and related generation parameters to api.mkkpro.com. Do not include secrets, regulated data, private customer information, or proprietary unreleased product details in prompts unless you have reviewed the provider's privacy and retention terms.

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
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill describes sending user-provided prompts to an external AI icon generation service but does not warn users that their text input will leave the local environment and be transmitted to a third party. This creates a privacy and data-handling risk because users may unknowingly submit sensitive internal project details, credentials, or proprietary descriptions to an external service.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
88% confidence
Finding

The sample response includes a URL on an external domain, confirming generated assets are hosted and retrieved from a third-party service. This is not inherently malicious, but it does represent external transmission and hosting of potentially sensitive generated content, which matters in environments with strict data residency or confidentiality requirements.

Content

Scanner excerpt · SKILL.md (reported line 37)May include surrounding context.

md
"style": "modern",
  "size": "256px",
  "format": "png",
  "url": "https://api.mkkpro.com/icons/icon_7a4k9m2x.png",
  "created_at": "2024-01-15T10:32:45Z",
  "expires_at": "2024-04-15T10:32:45Z",
  "download_count": 0

External Transmission

Medium
Category
Data Exfiltration
Confidence
90% confidence
Finding

The references section points users to external API endpoints and documentation, reinforcing that use of the skill depends on communicating with third-party infrastructure. In isolation this is expected for an API-backed skill, but without accompanying privacy and trust boundary disclosure it increases the risk of unintentional data exposure.

Content

Scanner excerpt · SKILL.md (reported line 111)May include surrounding context.

md
## References

- **Kong Route:** https://api.mkkpro.com/creative/ai-icon-generator
- **API Docs:** https://api.mkkpro.com:8002/docs

Static analysis

No suspicious patterns detected.