Back to skill

Security audit

Popup Cro

Security checks for vulnerabilities and agentic risk

Overview

This skill provides popup conversion advice and does not contain executable code, hidden persistence, or unrelated data-handling behavior.

Before installing, be aware that the skill may be invoked for a wide range of popup, modal, banner, or overlay conversion requests and may read local product-marketing context files if they exist. That behavior is disclosed and aligned with its purpose; keep confidential marketing context out of those files if you do not want it used in recommendations.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest description says to use the skill for popups, modals, overlays, slide-ins, banners, and then broadens further with 'Use this for any overlay or interrupt-style conversion element.' This activation scope is expansive and lacks clear exclusions, increasing the chance of unintended invocation for common UI discussions that may not be specifically about popup CRO.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The eval explicitly expects the skill to trigger on casual phrasing like 'our popups are annoying everyone,' which broadens activation beyond clear popup-optimization requests. In an agent routing context, this can cause unintended invocation of the popup-cro skill on ambiguous complaints or adjacent UX discussions, leading to misrouting, irrelevant guidance, or bypass of a more appropriate specialized skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.