ClawHub
Back to skill

Security audit

ecommerce-visual-copywriting

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed e-commerce copywriting workflow that asks for user-provided product details and produces compliant visual copy plans.

Install only where you want this e-commerce SOP to apply, and prefer explicit invocation if your agent auto-loads skills from broad keywords. Do not provide confidential product plans, pricing, or competitor materials unless you are comfortable using them in the copywriting workflow.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)

Agent Config Directory Access

High
Category
Agent Snooping
Confidence
90% confidence
Finding

Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.

Content

Scanner excerpt · README.md (reported line 143)May include surrounding context.

md
|------|-------------|------|
| **Cursor** | `.cursorrules` 或项目根目录 | 追加 SKILL.md 核心规则 |
| **Windsurf** | `.windsurfrules` | 同上 |
| **Continue** | `~/.continue/config.yaml` | 引用 SKILL.md 路径 |
| **Cline** (VS Code) | `.cline/` 目录 | 参考 Claude Code 方式 |
| **Aider** | `/instructions` 文件 | 复制 SKILL.md 内容 |
| **通用** | System Prompt / Custom Instructions | 直接嵌入核心规则 |

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 103)May include surrounding context.

bash
# 将 SKILL.md 放到项目根目录的 .claude/skills/ 下
mkdir -p .claude/skills/ecommerce-visual-copywriting
cp SKILL.md references/ .claude/skills/ecommerce-visual-copywriting/

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 110)May include surrounding context.

然后在 .claude/CLAUDE.md 中添加：

markdown
## 自定义 Skills

当用户请求电商文案设计时，读取并遵循 `.claude/skills/ecommerce-visual-copywriting/SKILL.md` 中的完整工作流。
合规规则参考 `.claude/skills/ecommerce-visual-copywriting/references/compliance-rules.md`。

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 110)May include surrounding context.

然后在 .claude/CLAUDE.md 中添加:

markdown
## 自定义 Skills

当用户请求电商文案设计时,读取并遵循 `.claude/skills/ecommerce-visual-copywriting/SKILL.md` 中的完整工作流。
合规规则参考 `.claude/skills/ecommerce-visual-copywriting/references/compliance-rules.md`。

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 112)May include surrounding context.

markdown
## 自定义 Skills

当用户请求电商文案设计时，读取并遵循 `.claude/skills/ecommerce-visual-copywriting/SKILL.md` 中的完整工作流。
合规规则参考 `.claude/skills/ecommerce-visual-copywriting/references/compliance-rules.md`。

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger keywords are very broad and include generic e-commerce and compliance terms such as 商品文案, 电商文案, 合规审查, and platform names. In tools that auto-activate skills based on keyword matching, this can cause the skill to fire during ordinary conversation and override the agent's normal behavior unexpectedly, increasing prompt-injection surface and causing mis-scoped instruction application.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger conditions include very common commerce terms such as '电商文案', '商品文案', 'listing', '产品页面', '转化率', and platform names, so the skill may activate during ordinary product or marketplace discussions even when the user did not request this SOP. Unintended invocation can derail the agent’s behavior, cause unnecessary collection of business data, and override more appropriate skills or general assistance flows.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.