ClawHub
Back to skill

Security audit

Career Success Planner

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to be a straightforward career-planning API integration that sends user-provided onboarding details to a disclosed remote service, with privacy caveats but no hidden or destructive behavior.

Before installing, confirm that your organization is comfortable sending employee onboarding and career assessment details to the listed external API. Avoid unnecessary direct identifiers, manager names, confidential performance information, or sensitive HR records unless you have appropriate consent and policy approval.

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
91% confidence
Finding

The skill solicits and transmits detailed professional and identifying data, including user identifiers, manager names, role details, experience history, and career goals, but provides no privacy notice, data minimization guidance, retention policy, or handling constraints. This creates a real privacy/security risk because sensitive employee assessment data could be exposed to a third-party service or processed in ways the user does not expect.

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, and the skill’s purpose is to send structured assessment content to that third-party service. In context, this is a real external transmission risk because the transmitted payload can contain sensitive employee and onboarding information, and the skill does not document trust boundaries, verification of the endpoint, or safeguards around outbound data sharing.

Content

Scanner excerpt · SKILL.md (reported line 202)May include surrounding context.

md
## References

- **Kong Route:** https://api.mkkpro.com/career/120-day-planner
- **API Docs:** https://api.mkkpro.com:8073/docs

Vague Triggers

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

This JSON manifest describes the POST operation simply as generating a "personalized 120-day career success plan" without any constraints, trigger scope, or exclusion conditions. In a manifest-style file, such broad invocation language can overlap with many general career-planning requests and may cause unintended activation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.