ClawHub
Back to skill

Security audit

Landing Optimizer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed marketing planning aid for influencer landing-page optimization, with no executable code or hidden high-impact behavior found.

Before installing, be aware that the skill may save landing-page URLs, promo codes, baseline conversion rates, and creator names into local memory. Use optional analytics or CMS connectors only with accounts you intend the agent to inspect for this campaign.

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 (2)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The template includes a full 'Performance Tracking' section with analytics, attribution, and post-launch metrics even though the skill metadata explicitly says post-launch measurement should use a different skill. This creates scope drift and can cause the agent to provide outputs outside its intended boundaries, leading to misuse, routing errors, and potentially inconsistent analytics guidance.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The display name, summary, and description include Chinese text by default, which imposes a bilingual locale choice in the skill's natural-language surface without indicating that the user can choose language. This can conflict with organizational language/locale policies when a skill should not force a specific language presentation unless documented or opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.