ClawHub
Back to skill

Security audit

Phishing Detection

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward URL phishing-check tool that sends only a submitted URL to an external analysis API.

Install this only if you are comfortable sending URLs you choose to analyze to the provider's external API. Avoid submitting private, internal, or token-bearing URLs unless the provider's privacy and retention practices meet your needs.

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 (2)

External Transmission

Medium
Category
Data Exfiltration
Content
# References

- **Kong Route:** `https://api.mkkpro.com/security/phishing-detection`
- **API Docs:** `https://api.mkkpro.com:8005/docs`
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The API operation is documented only as 'Check Url', without clear guidance on when the skill should be invoked, what inputs are appropriate, or what safety boundaries apply. In agent-integrated environments, vague operation descriptions can cause overbroad or unintended invocation on untrusted content, increasing the chance the agent sends sensitive or irrelevant URLs to an external phishing-analysis service.

Static analysis

No suspicious patterns detected.