ClawHub
Back to skill

Security audit

Embedded Systems

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent external roadmap API wrapper, but users should know it sends career-assessment details and identifiers to the provider.

Install only if you are comfortable sending career background, skills, goals, session identifiers, timestamps, and any optional user ID to the external roadmap service. Avoid including sensitive personal, employer-confidential, or unnecessary identifying information unless the provider's privacy terms 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 (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill documentation instructs users to send detailed assessment data along with tracking identifiers such as sessionId, userId, and timestamps to an external API, but it provides no disclosure about third-party data sharing, retention, or privacy implications. This creates a real privacy and security risk because users may submit personally linkable profiling data without informed consent or minimization.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
72% confidence
Finding

The file references an external API endpoint, confirming that skill use depends on sending data outside the local environment. By itself, an external URL is not automatically dangerous, but in this context it reinforces that user-supplied career assessment and tracking data are transmitted to a third-party service, which increases exposure if users are not clearly informed.

Content

Scanner excerpt · SKILL.md (reported line 181)May include surrounding context.

md
## References

- **Kong Route:** https://api.mkkpro.com/career/embedded-systems
- **API Docs:** https://api.mkkpro.com:8093/docs

Vague Triggers

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

For manifest-like API descriptions, ambiguous endpoint descriptions can cause unintended invocation when an agent is choosing among tools. 'Root' is highly generic and the description does not state concrete usage boundaries or exclusions.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

This is a manifest/config-style file, so vague-trigger review applies. The summary and description describe a general-purpose personalized roadmap generation action, but provide no narrowing context, explicit invocation scope, or negative examples to prevent overly broad matching by an agent that uses OpenAPI descriptions for tool selection.

Content

No source excerpt is available for this finding.