ClawHub
Back to skill

Security audit

Stacking

Security checks for vulnerabilities and agentic risk

Overview

This is a simple shopping-discount guidance skill with no executable code, though its wording is broader than a pure coupon calculator.

Before installing, understand that the skill may guide shopping decisions using more than coupon math, including shipping, seller trust, reviews, and after-sales information. Avoid sharing private order or account details unless you intentionally want those considered.

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 Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill documentation materially expands the apparent scope from a coupon-stacking calculator into logistics tracking, after-sales history, review analysis, buyer-show content, and livestream replay. This mismatch can mislead users and any calling agent about what data sources and permissions the skill may rely on, increasing the risk of over-collection of shopping, account, or behavioral data beyond the declared purpose.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The example invocation is phrased so broadly that ordinary help-seeking language could unintentionally trigger the skill outside narrowly intended coupon-calculation scenarios. Overbroad trigger phrases can cause accidental routing, leading users to disclose shopping preferences or order-related details to a skill they did not explicitly intend to invoke.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.