Wall Mounted Faucet Layout

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 9:32 AM UTC
• Version: 1.2.0

Overview

This skill is a focused wall-mounted faucet geometry calculator with proportionate local scripts and diagram assets.

Install this if you want an agent to calculate faucet layout dimensions or generate annotated SVG diagrams. Use clear project-specific output filenames for generated diagrams, and treat the results as geometric estimates that still need on-site verification.

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

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Rogue Agent: Self-Modification, Session Persistence
• Behavioral AST: exec() Call, eval() Call, Dynamic Import
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration

Findings (18)

Hidden Instructions

High

• Category: Prompt Injection
• Confidence: 70% confidence

Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · assets/wall_mounted_faucet_geometry_v2.svg (reported line 61)May include surrounding context.

text

<text x="50" y="48" class="title">Wall-mounted faucet and basin geometry</text>
  <text x="50" y="82" class="small">All horizontal distances use the finished wall as the common origin.</text>

  <!-- LEFT DIAGRAM -->
  <text x="50" y="125" class="subtitle">SIDE VIEW (cross-section)</text>

  <!-- Key x-coordinates:

Hidden Instructions

High

• Category: Prompt Injection
• Confidence: 70% confidence

Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · assets/wall_mounted_faucet_geometry_v2.svg (reported line 69)May include surrounding context.

text

outlet y=285, rim y=500, drain target y=755
  -->

  <!-- wall / counter -->
  <rect x="95" y="150" width="32" height="650" class="wall"/>
  <rect x="110" y="755" width="930" height="34" class="counter"/>

Hidden Instructions

High

• Category: Prompt Injection
• Confidence: 70% confidence

Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · assets/wall_mounted_faucet_geometry_v2_zh.svg (reported line 61)May include surrounding context.

text

<text x="50" y="48" class="title">壁挂式龙头与台盆几何关系</text>
  <text x="50" y="82" class="small">所有水平距离均以完成墙面为共同原点。</text>

  <!-- LEFT DIAGRAM -->
  <text x="50" y="125" class="subtitle">侧视图（剖面）</text>

  <!-- Key x-coordinates:

Hidden Instructions

High

• Category: Prompt Injection
• Confidence: 70% confidence

Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · assets/wall_mounted_faucet_geometry_v2_zh.svg (reported line 61)May include surrounding context.

text

<text x="50" y="48" class="title">壁挂式龙头与台盆几何关系</text>
  <text x="50" y="82" class="small">所有水平距离均以完成墙面为共同原点。</text>

  <!-- LEFT DIAGRAM -->
  <text x="50" y="125" class="subtitle">侧视图(剖面)</text>

  <!-- Key x-coordinates:

Session Persistence

Medium

• Category: Rogue Agent
• 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.

Content

Scanner excerpt · README.md (reported line 18)May include surrounding context.

Install as a user skill:

bash

mkdir -p ~/.codex/skills
git clone https://github.com/starsy/wall-mounted-faucet-layout-skill.git ~/.codex/skills/wall-mounted-faucet-layout

Skill Enumeration

Medium

• Category: Agent Snooping
• Confidence: 85% 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 18)May include surrounding context.

安装为用户级 skill:

bash

mkdir -p ~/.codex/skills
git clone https://github.com/starsy/wall-mounted-faucet-layout-skill.git ~/.codex/skills/wall-mounted-faucet-layout

Skill Enumeration

Medium

• Category: Agent Snooping
• Confidence: 85% 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.zh-CN.md (reported line 18)May include surrounding context.

安装为用户级 skill:

bash

mkdir -p ~/.codex/skills
git clone https://github.com/starsy/wall-mounted-faucet-layout-skill.git ~/.codex/skills/wall-mounted-faucet-layout

Session Persistence

Medium

• Category: Rogue Agent
• 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.

Content

Scanner excerpt · README.zh-CN.md (reported line 18)May include surrounding context.

安装为用户级 skill:

bash

mkdir -p ~/.codex/skills
git clone https://github.com/starsy/wall-mounted-faucet-layout-skill.git ~/.codex/skills/wall-mounted-faucet-layout

Skill Enumeration

Medium

• Category: Agent Snooping
• Confidence: 85% 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.

如果你的 Claude 运行环境支持本地 skill 目录:

bash

mkdir -p ~/.claude/skills
git clone https://github.com/starsy/wall-mounted-faucet-layout-skill.git ~/.claude/skills/wall-mounted-faucet-layout

Skill Enumeration

Medium

• Category: Agent Snooping
• Confidence: 85% 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.zh-CN.md (reported line 27)May include surrounding context.

如果你的 Claude 运行环境支持本地 skill 目录:

bash

mkdir -p ~/.claude/skills
git clone https://github.com/starsy/wall-mounted-faucet-layout-skill.git ~/.claude/skills/wall-mounted-faucet-layout

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 62)May include surrounding context.

---

When asked about wall-mounted faucet installation geometry, read and follow vendor/skills/wall-mounted-faucet-layout/SKILL.md. Prefer the deterministic calculator at vendor/skills/wall-mounted-faucet-layout/scripts/faucet_geometry.py.

text

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.zh-CN.md (reported line 62)May include surrounding context.

---

When asked about wall-mounted faucet installation geometry, read and follow vendor/skills/wall-mounted-faucet-layout/SKILL.md. Prefer the deterministic calculator at vendor/skills/wall-mounted-faucet-layout/scripts/faucet_geometry.py.

text

Ae4

Medium

• Category: analysis-evasion
• Confidence: 80% confidence

Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium

• Category: MCP Least Privilege
• Confidence: 87% confidence

Finding

The skill instructs the agent to generate an SVG file and explicitly write output to a user-visible path, but it does not declare any tool/permission scope limiting file-write behavior. In an agent framework, undeclared write capability increases the risk of unintended filesystem modification, path misuse, or writing artifacts to sensitive or unexpected locations if inputs are not constrained.

Content

No source excerpt is available for this finding.

Ae4

Medium

• Category: analysis-evasion
• Confidence: 80% confidence

Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Ae4

Medium

• Category: analysis-evasion
• Confidence: 80% confidence

Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 94% confidence

Finding

This SVG contains all user-facing labels and explanations in Chinese, as reflected in the title and subsequent annotations. Because the file provides no opt-in, alternative locale, or documented region-specific justification within the file, it appears to impose a specific language choice.

Content

No source excerpt is available for this finding.

Dynamic attribute access via getattr()

Low

• Category: Dangerous Code Execution
• Confidence: 50% confidence

Finding

Dynamic getattr() with a non-literal attribute name can access arbitrary object attributes, potentially bypassing access controls.

Content

Scanner excerpt · scripts/faucet_geometry.py (reported line 44)May include surrounding context.

python

a.WS = a.W / 2

    for name in REQUIRED_INPUTS[a.solve]:
        if getattr(a, name) is None:
            if name == "WS":
                parser.error(f"--WS is required when --solve {a.solve}, or provide --W to assume a centered drain")
            parser.error(f"--{name} is required when --solve {a.solve}")

Static analysis

No suspicious patterns detected.