ClawHub
Back to skill

Security audit

Financial Analyst

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward external career-roadmap API description, with expected user-supplied career data and no local execution or hidden behavior found.

Before installing, treat submitted assessment details as shared with the external API operator. Use an opaque sessionId, avoid sending sensitive personal or employment details that are not needed, and only provide userId if persistent profile tracking is desired.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly collects and transmits persistent identifiers such as sessionId and optional userId alongside detailed assessment and career-profile data, but provides no privacy notice, minimization guidance, retention limits, or warning that this can enable cross-session profiling. In a career-development context, this data can be used to track individuals over time, infer professional background and aspirations, and create unnecessary privacy risk if logged, shared, or breached.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
80% confidence
Finding

The skill directs users to an external API endpoint, which means submitted assessment data, timestamps, and identifiers will leave the local agent environment and be transmitted to a third-party service. External transmission is not inherently malicious, but without explicit disclosure of data handling, trust boundaries, and transport/privacy expectations, users may unknowingly expose personal or profile data to an external operator.

Content

Scanner excerpt · SKILL.md (reported line 212)May include surrounding context.

md
## References

- Kong Route: https://api.mkkpro.com/career/financial-analyst
- API Docs: https://api.mkkpro.com:8187/docs

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The API schema explicitly accepts sessionId, timestamp, and an optional userId, which are identifiers or metadata that can be linked to a user session. The OpenAPI spec does not describe any user-facing notice, consent language, data minimization, retention policy, or transport/privacy guarantees, creating a privacy risk through silent collection and transmission of potentially identifying data.

Content

No source excerpt is available for this finding.