Security audit

Landing Page Razor

Security checks for vulnerabilities and agentic risk

Overview

This is a benign landing-page writing and critique guide with no executable code or hidden access requests.

Safe to install for landing-page drafting or critique. Users should expect it to steer outputs toward minimal conversion-focused pages; if they want broader brand, content strategy, or multi-page website guidance, they may need to invoke a different skill or give explicit direction.

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
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)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The phrase "Use this when making or auditing a landing page" is very broad and does not clearly distinguish when this skill should activate versus when a more general writing, design, or marketing skill should be used. The file also lacks negative examples or exclusion conditions to constrain invocation scope.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.