Back to skill

Security audit

SEO Audit

Security checks for vulnerabilities and agentic risk

Overview

This is a simple SEO audit checklist skill with no executable code, persistence, credential handling, or hidden behavior.

Before installing, be aware that the trigger language is broad; use it when you specifically want an SEO audit, and provide only website data you are comfortable having analyzed. No artifact evidence indicates malicious behavior.

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
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
95% confidence
Finding

The manifest description says the skill performs comprehensive SEO audits but does not specify any explicit invocation phrases, scope limits, or exclusion conditions. In markdown/manifest content, this broad natural-language description can overlap with many generic requests about websites or marketing and may cause unintended invocation.

Content

No source excerpt is available for this finding.