ux-researcher
PassAudited by VirusTotal on May 10, 2026.
Overview
Type: OpenClaw Skill Name: ah-ux-researcher Version: 1.0.0 The skill bundle for 'ah-ux-researcher' contains only metadata and a markdown file (SKILL.md) defining a persona and workflow for a UX research assistant. There is no executable code, no network activity, and no evidence of malicious prompt injection or data exfiltration attempts.
Findings (0)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Private user research, analytics, or participant information could be brought into the agent context if the user or environment provides access.
The skill may cause an agent to retrieve or analyze user and product data, which is expected for UX research but can include sensitive participant or behavioral information.
Review existing user data, analytics, and design decisions
Use only authorized datasets, remove unnecessary personal data, and confirm consent and retention rules before sharing research materials with the agent.
Research findings or user data could be shared across agent roles if the surrounding system enables that collaboration.
The skill anticipates collaboration with other agents; this is purpose-aligned, but the artifact does not define data-sharing boundaries for research findings or participant data.
Integration with other agents: - Collaborate with product-manager on priorities - Work with ux-designer on solutions - Support frontend-developer on implementation
Share only the minimum research context needed with other agents, and avoid passing raw participant records or recordings unless explicitly required and approved.
The agent could overstate work performed or present unverified metrics as factual results.
The canned delivery notification contains specific research and impact metrics that could be misleading if repeated without being true for the actual task.
UX research completed. Conducted 12 studies with 247 participants, generating 89 actionable insights. Improved task completion rate by 34% and reduced user errors by 58%.
Treat these numbers as placeholders only; require the agent to report actual study counts, participant counts, and measured outcomes, or state when they are examples.