ClawHub
Back to skill

Security audit

Investment Banking

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow investment-banking career roadmap API integration with expected profile-data use, but users should be aware that career assessment details may be sent to an external service.

Before installing, consider whether you are comfortable sending career assessment details, identifiers, employer information, skills, certifications, goals, and location preferences to the referenced external API. Avoid submitting sensitive personal details that are not needed for career guidance.

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 (5)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill includes realistic examples of sensitive personal and career-profile data such as employer, experience history, geographic preference, certifications, and user/session identifiers, but provides no privacy notice, minimization guidance, retention limits, or handling requirements. In a career-planning context this data can be identifying or profile-building, increasing the risk of unnecessary collection, downstream sharing, or misuse if integrators copy the example schema directly into production.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
82% confidence
Finding

The skill references an external API endpoint, which implies user-supplied assessment and profile data may be transmitted to a third-party service outside the immediate skill environment. Without explicit trust boundaries, security assurances, or data processing disclosures, this creates risk of unintended data exposure, especially because the skill handles career and potentially identifying information.

Content

Scanner excerpt · SKILL.md (reported line 226)May include surrounding context.

md
## References

- **Kong Route:** https://api.mkkpro.com/career/investment-banking
- **API Docs:** https://api.mkkpro.com:8186/docs

Vague Triggers

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

This is a manifest/config-style file, so vague-trigger checks apply. The operation is described only as 'Generate Roadmap' / 'Generate personalized Investment Banking roadmap' with no narrowing conditions, explicit trigger phrases, or negative examples, which can make activation intent overly broad.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The phrase 'Get Specializations' with description 'Get available specialization paths' is generic and does not specify context, constraints, or exclusions. In a manifest-like API description, this can create ambiguity about when this capability should be selected versus other nearby capabilities.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The summary and description say only 'Get Learning Paths' and 'Get all available learning paths,' which are broad and lack explicit trigger scope. Without clearer boundaries or examples, this can overlap with common requests for advice or educational guidance.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.