ClawHub
Back to skill

Security audit

AI Logo Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward AI logo API wrapper, with the main consideration being that logo prompts are sent to an external service.

Install only if you are comfortable sending logo descriptions to the listed external API; avoid including confidential brand strategy, unreleased product names, regulated data, or secrets in prompts.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill documentation encourages users to submit natural-language prompts and consume returned logo URLs, but it does not disclose that prompts are sent to a third-party external API and that outputs are hosted on external infrastructure. This creates a privacy and trust issue: users may unknowingly transmit sensitive business, branding, or proprietary information to an outside service and later fetch remote content from an unvetted domain.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
86% confidence
Finding

The skill references an external endpoint, confirming that user input and service interaction leave the local trust boundary. In this context, external transmission is not inherently malicious because the skill is API-backed by design, but it is still security-relevant because prompts may contain sensitive information and the returned logo_url may cause clients to retrieve remote content from third-party infrastructure.

Content

Scanner excerpt · SKILL.md (reported line 95)May include surrounding context.

md
## References

- **Kong Route:** `https://api.mkkpro.com/creative/ai-logo-generator`
- **API Docs:** `https://api.mkkpro.com:8003/docs`

Vague Triggers

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

This JSON file is a manifest-type file, so vague-trigger checks apply. The operation is described only as "Generate Logo" with no constraints, examples, or exclusion conditions, leaving activation scope overly broad and making it unclear what kinds of requests or prompts are intended versus out of scope.

Content

No source excerpt is available for this finding.