ClawHub
Back to skill

Security audit

Fitness Plan Flows

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent prompt-and-template package for designing fitness accessory marketing flows, with no hidden privileged behavior found.

This appears safe to install as a marketing-planning skill. Review generated email/SMS flows before deploying them in tools like Klaviyo or Shopify Email, especially for customer consent, promotion terms, and avoiding medical or therapeutic 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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

Yes, this is a mismatch. The description claims a substantive skill for generating actionable marketing flow designs for fitness accessory merchants, but the provided code is effectively blank and does not implement that purpose. There are no undeclared harmful capabilities or resource accesses; the mismatch is that the actual code does not perform the declared function at all.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.