Back to skill

Security audit

AI Brand Visibility Check

Security checks for vulnerabilities and agentic risk

Overview

This is a small disclosed marketing-research skill that points agents to a paid external brand-visibility check, with no bundled code or persistence.

Before installing, users should be comfortable with agents contacting store.agentexchange.work with brand names and potentially approving small USDC x402 payments; agents should avoid using it automatically for broad marketing work unless a live AI-brand-visibility check is actually desired.

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

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The description says to use the skill when 'auditing a brand's AI visibility, doing competitive marketing research, writing a GEO/marketing report, or answering "does AI recommend us".' These are broad natural-language situations rather than specific trigger phrases or constrained activation conditions, which may cause unintended invocation for general marketing or research requests.

Content

No source excerpt is available for this finding.