ClawHub
Back to skill

Security audit

Product Description Writer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent e-commerce copywriting helper with only local, disclosed helper scripts and no evidence of hidden data access, persistence, or unsafe behavior.

Before installing, note that the skill may activate for product-spec or competitor-listing rewrite requests, and its helper scripts can read and write local files you point them at. Review generated copy for unsupported claims, especially health, beauty, certification, or performance claims.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding
The declared description says the skill should generate or rewrite sellable e-commerce copy across many product-copywriting scenarios. The supplied code does not generate, rewrite, or optimize copy content; it only analyzes an existing markdown file for predefined quality heuristics and reports issues. While the checks are related to product-description quality and SEO, the primary purpose is materially different: validation/linting instead of copy creation. No undeclared sensitive permissions are present, but the functionality does not match the declared skill behavior.

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding
The declared purpose promises end-output copywriting capability: producing high-converting, SEO-optimized product descriptions and related listing assets. The actual code only structures provided product data into a markdown brief for later use by the skill or a human copywriter. While the brief is related to product-description workflows, the primary behavior is preparatory templating, not actual copy generation. There is no logic that writes product descriptions, rewrites competitor listings, translates features into benefits, or optimizes SEO content. Therefore, the description materially overstates what this code chunk does.

Lp3

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

Vague Triggers

Medium
Confidence
92% confidence
Finding
The manifest description says to use the skill whenever the user mentions many product-copy terms and also when they paste a spec sheet, feature list, ingredient list, or competitor listing and want it 'rewritten' or 'improved' even without explicitly saying 'product description.' That activation condition is broad enough to overlap with generic editing or summarization requests, which could cause unintended invocation despite the later 'When NOT to use this skill' section.

Static analysis

No suspicious patterns detected.