ClawHub
Back to skill

Security audit

RPA Developer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple hosted roadmap generator that discloses the assessment data it sends, with a privacy-documentation gap users should consider.

Before installing, treat the assessment answers, sessionId, timestamp, and optional userId as data sent to the provider's API. Use an anonymous or pseudonymous userId where possible, avoid entering sensitive personal details beyond what is needed for the roadmap, and review the provider's privacy terms if retention or sharing matters to you.

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 requests persistent identifiers (sessionId, userId, timestamps) and detailed assessment data about a user's experience, skills, and goals, but provides no privacy notice, retention guidance, consent language, or data-handling limitations. This creates a real privacy and compliance risk because users or integrators may transmit personally linkable profiling data to a third-party service without understanding how it is stored, shared, or protected.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 220)May include surrounding context.

md
# References

- **Kong Route:** https://api.mkkpro.com/career/rpa-developer
- **API Docs:** https://api.mkkpro.com:8068/docs

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

This manifest/OpenAPI file documents request fields including sessionId, timestamp, and optional userId, as well as nested assessment data, but provides no warning or disclosure about collecting or transmitting this user-linked data. For markdown and manifest-style descriptions, the audit criteria call for warning users when behavior may affect privacy or user data.

Content

No source excerpt is available for this finding.