ClawHub
Back to skill

Security audit

Backend Developer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward API-backed backend-career roadmap generator, with some personal career data sharing users should understand before use.

Before installing, users should be comfortable sending career assessment details, goals, session identifiers, and optional user IDs to the referenced external service. Avoid entering sensitive employer, proprietary project, or unnecessary identifying information unless the service's privacy terms 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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill solicits and exemplifies collection of user-linked assessment data, including session identifiers, user IDs, experience history, and career goals, but provides no privacy notice, retention guidance, consent expectations, or restrictions on downstream sharing. Because this data is sent to an external roadmap-generation service, users and integrators may unknowingly expose profiling data and identifiers without adequate disclosure or minimization.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
80% confidence
Finding

The skill references an external API endpoint, which means user-supplied assessment data is likely transmitted outside the local trust boundary to a third-party service. In this skill's context, the transmitted content includes profile-like information about experience, skills, and career goals, increasing the risk of unintended disclosure, compliance issues, or reliance on an unvetted remote service.

Content

Scanner excerpt · SKILL.md (reported line 199)May include surrounding context.

md
## References

- **Kong Route:** https://api.mkkpro.com/career/backend-developer
- **API Docs:** https://api.mkkpro.com:8085/docs

Vague Triggers

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

This is a manifest-style file, so vague-trigger checks apply. The summary and description for the POST operation only say "Generate Roadmap" and "Generate personalized backend developer roadmap" without any explicit activation constraints, trigger examples, or exclusion conditions, making invocation scope ambiguous.

Content

No source excerpt is available for this finding.