Back to skill

Security audit

multisim-compare-experiments

Security checks for vulnerabilities and agentic risk

Overview

This skill only guides comparison of two registered Multisim experiments and does not include hidden execution, persistence, or broad data access.

Install this if you use Multisim experiment IDs and are comfortable with the agent reading selected experiment summaries and text artifacts to compare results. Non-Chinese users may want to ask the agent to respond in their preferred language.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill content is primarily in Chinese and does not offer a language choice or adapt to the user's language. This can cause misunderstanding of required inputs, comparison limits, or output expectations, which may lead users to misuse the skill or misinterpret results, but it is not a direct security exploit vector.

Content

No source excerpt is available for this finding.