Product Ux Audit

• Outcome: Pass
• Latest audit: Oct 12, 2026 · 6:38 AM UTC
• Version: 0.1.0

Overview

This skill is a disclosed read-only product and UX audit workflow that reads scoped project files and writes local reports, with no evidence of hidden, destructive, or exfiltrating behavior.

Install only if you want an agent to read scoped parts of your codebase and generate local audit reports. Review or choose the output folder if Desktop is synced or shared, and be deliberate before using the optional multi-agent pipeline because it can increase tool usage and duplicate repo-reading across subagents.

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
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (7)

Skill Enumeration

Medium

• Category: Agent Snooping
• Confidence: 80% confidence

Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · README.md (reported line 27)May include surrounding context.

md

## How to Use

1. **Install:** Save `SKILL.md` into `~/.claude/skills/product-ux-audit/SKILL.md`. Restart your agent session — the skill becomes available as `/product-ux-audit`.
2. **Invoke with a defined scope:** One user flow at a time — e.g. `/product-ux-audit. Scope: auth-onboarding. Files: src/app/(auth)/*, src/api/auth.ts`. See Scope Discipline in SKILL.md — never point it at an entire repository in one pass.
3. **Read the report:** Phase reports plus a final summary are written to `%USERPROFILE%\Desktop\_Reports\<timestamp>\` (Windows) or `~/Desktop/_Reports/<timestamp>/` (Linux/macOS) — never inside the project repository.
4. **Auditing a whole product?** See the pipeline section below — generate a task list first, then run it one scope at a time.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 97% confidence

Finding

The skill description includes broad trigger phrases such as product audit, UX audit, usability check, and heuristic evaluation, which can cause unintended invocation for ambiguous everyday requests. Over-broad activation increases the chance that the agent performs a large, multi-phase audit when the user wanted a narrower review, leading to unnecessary repository scanning and scope overreach.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium

• Category: Not specified by scanner
• Confidence: 84% confidence

Finding

The optional benchmark phase permits mapping features against competitors and references external data if the user provides it, which broadens the skill from repo analysis into externally informed analysis. This is not inherently malicious, but it can cause unintended scope expansion and potentially prompt unnecessary handling of non-repo data in a skill otherwise framed as a codebase audit.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium

• Category: Not specified by scanner
• Confidence: 91% confidence

Finding

The skill explicitly instructs spawning fresh subagents to validate findings, which expands its operational capabilities beyond a normal read-only product/UX audit. In an agentic environment, this can increase tool use, cost, and data exposure surface by sending repository context or findings to additional agents without a strict necessity for the requested task.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low

• Category: Not specified by scanner
• Confidence: 89% confidence

Finding

The README states that the skill writes output to the user's Desktop outside the project tree, which creates files in a user-owned location that may be unexpected and could expose sensitive audit results to other local users, backup/sync tools, or screenshot/indexing workflows. While not inherently malicious, the behavior should be clearly disclosed as an out-of-repo write with privacy implications and ideally require explicit user consent or configuration.

Content

No source excerpt is available for this finding.

Vague Triggers

Low

• Category: Not specified by scanner
• Confidence: 88% confidence

Finding

The trigger guidance lists several positive examples but does not define clear boundaries for near-matches, such as generic feedback requests or high-level product discussion. Without negative examples, the activation scope remains somewhat ambiguous and may overlap with normal conversation or other review skills.

Content

No source excerpt is available for this finding.

Scope Creep

Low

• Category: Excessive Agency
• Confidence: 75% confidence

Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · SKILL.md (reported line 283)May include surrounding context.

md

- **READ-ONLY** on project source. Zero writes inside the repository — reports only go to `$outDir` under `_Reports`.
- **Evidence-only**: every finding cites a file:line, screen name, or concrete code excerpt. No speculation framed as fact.
- **Timestamped output** — never overwrite previous runs.
- **Scope discipline**: don't silently expand scope to the whole app; if you think broader scope is warranted, say so in the summary instead of just doing it.
- **No overlap duplication with forensic-audit**: if a security/data-integrity issue surfaces, note it briefly with a pointer ("see forensic-audit for security depth") rather than producing a full security finding here.
- **Severity = user/business impact**, not exploitability or code elegance.

Static analysis

No suspicious patterns detected.