ClawHub
Back to skill

Security audit

CyberSec Cert Advisor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent career-advice API integration, but users should be mindful that professional profile details may be sent to an external service.

Before installing, users should understand that submitted career details, certifications, tools, interests, goals, timestamps, session IDs, and optional user IDs may be processed by the external API. Avoid sending unnecessary identifying information unless the provider's privacy and retention practices are acceptable.

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
Confidence
90% confidence
Finding
The skill requests potentially identifiable career-assessment data, including userId, session identifiers, timestamps, employment details, certifications, and salary-related profiling inputs, but provides no privacy notice, data handling disclosure, retention policy, or explanation of analytics use. This creates a real privacy and compliance risk because users may disclose personal and professional profile data without informed consent or understanding where it is stored, shared, or processed.

External Transmission

Medium
Category
Data Exfiltration
Content
## References

- **Kong Route:** https://api.mkkpro.com/career/cert-advisor
- **API Docs:** https://api.mkkpro.com:8074/docs
Confidence
78% confidence
Finding
The skill references an external API endpoint, meaning user-supplied assessment data is likely transmitted off-platform to a third-party service. In the context of this skill, the transmitted data includes professional background and potentially identifying metadata, so undocumented external transmission increases confidentiality, trust, and compliance risk even if the endpoint itself is not overtly malicious.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The API accepts assessment data along with session and optional user identifiers, but the specification provides no privacy, retention, or handling disclosures. In a career-advisory context, these fields can reveal sensitive professional profiling data, and the absence of documented data-handling expectations increases the risk of overcollection, misuse, or insecure downstream integration.

Vague Triggers

Low
Confidence
81% confidence
Finding
This is a manifest/config file, so vague-trigger review applies. The description 'Generate personalized certification and career plan' states the action but does not define triggering scope, constraints, or exclusion conditions, making invocation conditions ambiguous in systems that derive activation behavior from OpenAPI descriptions.

Static analysis

No suspicious patterns detected.