Security audit

特朗普.skill - 谈判与权力思维操作系统

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese-language prompt skill for analyzing or role-playing Donald Trump's perspective, with no executable code, persistence, or data access.

Install this only if you want a Chinese-language political analysis and roleplay aid. Treat its predictions and current-event claims as opinionated framing, and verify time-sensitive political facts independently.

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: 95% confidence
Finding: The skill metadata and activation examples are written entirely in Chinese and imply Chinese-first interaction behavior without checking the user's language preference. This can cause unintended language switching, reduce user comprehension, and create a prompt-steering issue where the agent responds in a language the user did not request.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.