Back to skill

Security audit

守拙 — 中国基金经理心智模型

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese-market investment analysis persona with no code, network access, persistence, or trading authority, but users should treat its output as opinionated financial analysis rather than advice.

Install only if you want an opinionated Chinese-language value-investing framework for China-market discussion. Use explicit invocation such as “用守拙视角分析” to avoid accidental activation, verify all market data independently, and do not treat generated buy/sell or position-sizing language as personalized financial advice.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger phrase list includes broad, common investment terms such as '价值投资', '中国股市', '基金配置', and '选股逻辑', which can cause the skill to activate during ordinary financial discussion without clear user intent. This creates an unnecessary prompt-routing surface where the agent may be steered into this persona unexpectedly, increasing the risk of inappropriate advice framing or context hijacking.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The example invocation phrases are still broad enough to match normal investment questions, especially phrases like '估值是否合理' or '应该逆向买入吗', which do not uniquely identify this skill. In a multi-skill environment, ambiguous invocation increases the chance of accidental activation and unintended behavioral override, even if the content itself is not overtly malicious.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The description defines the skill as a China-market persona focused on A股/港股 and presents the instructions entirely in Chinese without offering users a language or locale choice. Under the policy, a fixed language/locale should either be optional or explicitly justified as a region-specific tool.

Content

No source excerpt is available for this finding.