ClawHub
Back to skill

Security audit

UX QA Gate

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed UX self-review checklist with no executable code, credential handling, persistence, or hidden data movement.

Install this if you want Codex to run a UX QA checklist before delivering frontend or user-facing changes. Be aware it may add extra review steps after UI work, and locale-related checks should follow your explicit product requirements or user preferences.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is configured to run automatically after virtually any user-facing change, including broad conditions like finishing a build task or wrapping up frontend work. Overly broad auto-invocation can cause the agent to trigger this skill in situations where it is unnecessary, increasing prompt surface area, consuming context, and potentially interfering with normal task completion or causing repeated recursive/self-check behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The checklist item says dates, currency, and units should match the target audience expectations, which can be read as prescribing a locale based on audience assumptions rather than user-selected preference. Under the policy, language or locale requirements should either offer user choice or be clearly justified as region-specific.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.