Form UX Best Practices

• Outcome: Pass
• Latest audit: Sep 11, 2026 · 5:02 AM UTC
• Version: 1.0.0

Overview

This skill appears to be a straightforward form UX and accessibility audit aid with a disclosed optional local HTML checker and no hidden persistence or data exfiltration.

This is reasonable to install for form UX and accessibility review. Only run the optional Python audit on form HTML files you intend to inspect, and only use the README's optional API upload command if you understand that it sends the packaged skill to the OpenAI Skills API with your API key.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Rogue Agent: Self-Modification, Session Persistence
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands

Findings (4)

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 92% confidence
• Finding: The code is clearly related to form accessibility auditing, so it is in the same general domain as the description. However, the declared purpose promises a much broader, opinionated workflow that can review form specs or implementations and produce prioritized UX/accessibility/copy fixes, rewrites, validation/error-message specs, and optional implementation pseudo-code. The supplied code does none of that generation or broader review; it only performs a narrow static analysis of an HTML file for a specific set of markup issues. This is a material description-to-behavior mismatch in primary capability breadth, even though the code partially overlaps the accessibility audit portion of the description.

Session Persistence

Medium

• Category: Rogue Agent

Content

It provides a deterministic workflow to:
- Review a form spec or implementation
- Prioritize issues (P0/P1/P2)
- Rewrite fields and validation copy
- Produce an accessibility checklist and ship-ready QA checklist
- Optionally output ready-to-ship HTML/React pseudo-code

• Confidence: 60% confidence
• Finding: Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

External Transmission

Medium

• Category: Data Exfiltration

Content

cd /path/to/repo-root
zip -r form-ux-best-practices.zip form-ux-best-practices

curl https://api.openai.com/v1/skills \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -F "file=@form-ux-best-practices.zip"
```

• Confidence: 50% confidence
• Finding: Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 70% confidence
• Finding: Without declared permissions the skill's intent is opaque and cannot be validated.

Static analysis

No suspicious patterns detected.