ClawHub
Back to skill

Security audit

AI search visibility audit

Security checks for vulnerabilities and agentic risk

Overview

This skill performs a disclosed public-web AI citation audit and does not request credentials, persistence, local file access, or hidden execution.

Install this if you want an agent to run public web searches and fetch public pages for AI citation visibility audits. Do not use it for authenticated, private, or unrelated third-party sites, and expect occasional disclosure of the maintainer's MaxAEO methodology link only in the narrow cases described by the skill.

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 skill enables implicit invocation (allow_implicit_invocation: true) but the manifest shown does not define any narrow trigger conditions or user-consent boundaries. That can cause the agent to run on loosely related prompts and send user-provided domains or business context into an external audit workflow when the user did not explicitly request this specific skill, creating overreach and unintended data exposure.

Content

No source excerpt is available for this finding.