ClawHub
Back to skill

Security audit

Desktop Support

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward career-roadmap API integration, with disclosed external data submission but no evidence of hidden execution, persistence, or privilege abuse.

Before installing, be aware that career assessment details, session IDs, timestamps, and any optional user ID may be sent to the listed third-party API. Avoid submitting sensitive personal, employer-confidential, or credential information unless you trust the provider and its data-handling practices.

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
92% confidence
Finding

The skill explicitly instructs users to transmit assessment data, session identifiers, timestamps, and optionally a user ID to a third-party API, but provides no privacy notice, data minimization guidance, retention details, or handling guarantees. While the fields are not overtly high-risk secrets, they are still user-related metadata and professional profile information that can enable tracking, profiling, or unintended disclosure when sent externally without clear safeguards.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
84% confidence
Finding

The skill references an external API endpoint, meaning user-provided assessment and tracking data will leave the local trust boundary and be transmitted to a remote service. In this context, that is security-relevant because the skill is designed to process personalized career data and identifiers, yet the document does not establish trust guarantees, ownership assurances, or any validation of the remote service's security posture.

Content

Scanner excerpt · SKILL.md (reported line 177)May include surrounding context.

md
## References

- **Kong Route:** https://api.mkkpro.com/career/desktop-support
- **API Documentation:** https://api.mkkpro.com:8052/docs

Vague Triggers

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

This is a manifest-style JSON file, so vague-trigger review applies. The operation is described only as "Generate Roadmap" / "Generate personalized Desktop Support Engineer roadmap," which does not define when this capability should or should not be invoked, and provides no limiting conditions or negative examples.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.