Back to skill

Security audit

Signup

Security checks for vulnerabilities and agentic risk

Overview

This is a signup-flow optimization guidance skill with no code execution, persistence, or hidden data access.

Installers should understand that this skill may be selected for loosely phrased signup-conversion questions and may read a local product-marketing context file if one exists, but the inspected artifact is advisory and does not execute code or make changes.

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
86% confidence
Finding

The description says to use the skill whenever a user has a signup or registration flow that 'isn't performing,' alongside broad phrases like 'people aren't signing up' and 'simplify our signup.' This creates an ambiguous trigger boundary because many general product, growth, or UX discussions could match without clearly indicating this specific skill should activate instead of related skills.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The eval explicitly rewards triggering on 'casual phrasing,' which broadens routing criteria and can cause the signup skill to activate on vague requests that may belong to other skills. In this context, over-broad dispatch can produce incorrect guidance, suppress more appropriate skills such as CRO or onboarding, and increase the chance of unintended behavior from loosely matched prompts.

Content

No source excerpt is available for this finding.