吴军 AI 趋势

• Outcome: Pass
• Latest audit: Sep 12, 2026 · 8:25 AM UTC
• Version: 2.0.0

Overview

This skill is a coherent Chinese-language AI trend and investment-analysis helper with no evidence of hidden persistence, credential access, destructive behavior, or exfiltration.

Install only if you want Chinese-language AI trend and investment-framework assistance. Treat any investment output as a research checklist, not financial advice, and be aware that running the helper with --search may query an external searxng-based search tool if that sibling skill exists.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Behavioral AST: exec() Call, eval() Call, Dynamic Import
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration

Findings (6)

Natural-Language Policy Violations

Medium

• Confidence: 90% confidence
• Finding: The README is entirely presented in Chinese and describes the skill as being based on Chinese investment masters, with no indication that users may choose another language or locale. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 70% confidence
• Finding: Without declared permissions the skill's intent is opaque and cannot be validated.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The activation text uses broad triggers such as 'when users need to analyze AI trends' and 'when asking where AI investment opportunities are,' which can cause the skill to activate in many loosely related contexts. This is not directly exploitable like code execution, but it can lead to over-selection of the skill, increasing the chance of irrelevant financial-style guidance being injected into conversations where it is not appropriate.

Natural-Language Policy Violations

Medium

• Confidence: 94% confidence
• Finding: The file’s natural-language description and all user-facing output are written exclusively in Chinese, and the default topic is also Chinese. There is no indication that the skill is region-specific or that users can opt into another language, which matches the policy category for forced language/locale behavior.

subprocess module call

Medium

• Category: Dangerous Code Execution

Content

'--format', 'json'
            ]
            
            proc_result = subprocess.run(cmd, capture_output=True, text=True, timeout=15)
            
            if proc_result.returncode == 0:
                search_data = json.loads(proc_result.stdout)

• Confidence: 70% confidence
• Finding: subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Natural-Language Policy Violations

Low

• Confidence: 88% confidence
• Finding: This markdown template is entirely written in Chinese and does not indicate that users may choose another language or that the template is intentionally restricted to a Chinese-speaking audience. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.

Static analysis

No suspicious patterns detected.