ClawHub
Back to skill

Security audit

CyberSec Roadmap V2

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed external API integration for generating cybersecurity learning roadmaps, with some privacy notes around profile and session data but no hidden or unsafe behavior found.

Before installing, understand that assessment answers and request identifiers may be sent to the provider's external API. Avoid entering sensitive personal, employer-confidential, or credential information, and use pseudonymous session or user identifiers when possible.

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
92% confidence
Finding

The skill explicitly collects user/session identifiers, timestamps, and detailed assessment data about a user's background and goals, but provides no disclosure about storage, retention, sharing, or minimization. This creates a privacy and governance risk because consumers may transmit identifying or profiling data to a third-party service without informed consent or clear handling guarantees.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
76% confidence
Finding

The skill directs users to an external API endpoint, which means user-supplied assessment data and identifiers may be transmitted outside the local trust boundary. By itself, referencing an external service is normal, but in this context it becomes security-relevant because the skill does not document authentication, transport assurances, data handling, or trust expectations for the remote endpoint.

Content

Scanner excerpt · SKILL.md (reported line 256)May include surrounding context.

md
## References

- **Kong Route:** https://api.mkkpro.com/career/cybersec-roadmap-v2
- **API Docs:** https://api.mkkpro.com:8109/docs

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The schema explicitly collects and transmits sessionId, timestamp, and optional userId fields, but the spec provides no privacy notice, purpose limitation, retention guidance, or indication of whether these identifiers are necessary. In a learning-roadmap skill, this increases unnecessary tracking and correlability risk, especially if session and user identifiers are logged or reused across requests.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

This is a manifest-style OpenAPI file, so vague-trigger checks apply. The endpoint is described only as "Generate Roadmap" / "Generate personalized cybersecurity roadmap" without any limiting conditions, explicit trigger phrases, or exclusion examples, which leaves activation scope underspecified for systems that may derive skill invocation behavior from the manifest text.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.