ClawHub
Back to skill

Security audit

UX Research Engine

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only UX research skill with purpose-aligned templates, but users should apply normal privacy and consent controls when handling participant data.

Install only if you are comfortable using it as a UX research template library. Before storing real participant data, confirm informed consent, collect only necessary demographics, restrict repository access, de-identify notes where possible, and define retention/deletion rules for recordings and raw study material.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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 (2)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill instructs users to store recordings, per-participant notes, demographics, and raw study artifacts in a research repository, but it does not pair that guidance with any privacy, consent, retention, access-control, or de-identification safeguards. In a UX research context this can lead to unnecessary collection and long-term storage of sensitive participant data, increasing risk of privacy violations, unauthorized access, and regulatory noncompliance.

Natural-Language Policy Violations

Low
Confidence
79% confidence
Finding
The screener template includes `language: "[e.g., English-fluent]"` as the example participant requirement, which can normalize a fixed language constraint without documenting user choice or regional justification. The policy allows locale constraints when justified, but here the example is presented generically rather than as an optional, context-specific condition.

Static analysis

No suspicious patterns detected.