Security audit

Mp Prototype

Security checks for vulnerabilities and agentic risk

Overview

This skill gives ordinary guidance for creating clearly marked throwaway prototypes and does not show hidden, persistent, deceptive, or data-exfiltrating behavior.

Before installing, expect this skill to create temporary prototype code in your project and to leave notes about the prototype decision. Review generated prototype files before keeping or merging them, especially because the skill intentionally skips production polish and tests.

A.I.G

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

SkillSpector

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)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The description mixes English instructions with Chinese-only trigger guidance ('当用户需要原型...时使用'), which imposes a locale-specific activation description without stating that language support is optional or user-selected. This can violate language/locale policy because it privileges one language without explicit opt-in or justification.
Content: No source excerpt is available for this finding.