Back to skill

Security audit

AIOT Engineer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward external API wrapper for AIoT career roadmap generation, with routine privacy considerations because it sends user-provided assessment data to a service.

Before installing, understand that roadmap generation sends the assessment information you provide, including career goals, skills, session IDs, timestamps, and optional user ID, to the provider's external API. Avoid entering sensitive personal, employer-confidential, or credential data unless you intend to share it with that service.

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
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
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 216)May include surrounding context.

md
## References

- **Kong Route:** https://api.mkkpro.com/career/aiot-engineer
- **API Docs:** https://api.mkkpro.com:8097/docs

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

This markdown file describes collecting and transmitting assessment data, session identifiers, timestamps, and optional user IDs to generate personalized roadmaps. While the behavior is core to the skill, the documentation does not include any user-facing warning or disclosure about handling potentially identifying profile data or privacy implications.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The OpenAPI title and description are defined only in English, and the rest of the user-facing summaries/descriptions follow the same pattern. For skills subject to organizational language policy, forcing a single language without documented user opt-in or locale choice can violate language/locale requirements.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

This is a manifest-style file, so vague-trigger checks apply. The endpoint description 'Generate personalized AIoT engineering roadmap' states a general activation behavior but provides no constraints, scoping details, or negative examples indicating when this capability should or should not be invoked, which can make invocation boundaries ambiguous in agent tooling that derives triggers from OpenAPI descriptions.

Content

No source excerpt is available for this finding.