Back to skill

Security audit

Learn Crossover

Security checks for vulnerabilities and agentic risk

Overview

This is a teaching-method skill that helps explain new concepts by analogy and does not request code execution, persistence, credentials, or broad data access.

Installers should expect the skill to ask what topics, tools, or projects they already know so it can build analogies. Avoid sharing confidential project details if a high-level description is enough.

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

Defining the skill for virtually any situation involving unfamiliarity or difficulty makes activation ambiguous and highly overlapping with general tutoring, explanation, and help flows. This ambiguity can lead to inappropriate invocation frequency, making agent behavior less controllable and potentially causing irrelevant questioning about user background when the user only wanted a direct answer.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

Defining the skill for virtually any situation involving unfamiliarity or difficulty makes activation ambiguous and highly overlapping with general tutoring, explanation, and help flows. This ambiguity can lead to inappropriate invocation frequency, making agent behavior less controllable and potentially causing irrelevant questioning about user background when the user only wanted a direct answer.

Content

No source excerpt is available for this finding.