ClawHub
Back to skill

Security audit

Automation Tester

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward external API integration for generating automation tester career roadmaps, with disclosed input fields and no evidence of hidden execution, persistence, or destructive behavior.

Install only if you are comfortable sending automation testing career assessment details, session identifiers, timestamps, and an optional user ID to the provider's external API. Avoid including unnecessary personal or confidential employer information in the assessment fields.

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 (4)

External Transmission

Medium
Category
Data Exfiltration
Content
## References

- **Kong Route:** https://api.mkkpro.com/career/automation-tester
- **API Docs:** https://api.mkkpro.com:8063/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
82% confidence
Finding
This is a manifest-style OpenAPI file, so vague-trigger checks apply. The description "Generate personalized automation tester roadmap" is broad and provides no constraints, trigger conditions, or exclusions, which could lead to unintended invocation whenever a user mentions roadmap generation in a general sense.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The OpenAPI spec defines transmission of potentially identifying fields such as sessionId, userId, and timestamp, but the endpoint description contains no disclosure about sending or storing this data. For this file type, the natural place for the warning would be in the API/skill description, and none is present here.

Missing User Warnings

Low
Confidence
82% confidence
Finding
The markdown describes collecting assessment data along with sessionId, timestamp, and optional userId, which can affect user privacy and tracking. Under the markdown-file warning criterion, the skill should disclose privacy-relevant handling when user-related data is part of the workflow, but no warning or notice is present nearby or elsewhere in the document.

Static analysis

No suspicious patterns detected.