Back to skill

Security audit

高瓴资本投资框架

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only Chinese investment-analysis framework with broad trigger phrases but no code, persistence, or data-access behavior.

Before installing, understand that the skill may activate on broad investment terms and frame answers through a Hillhouse-style lens. Treat its output as an analytical framework, not licensed financial advice, and ask for another language or a different framework when needed.

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 (14)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation phrases are broad, generic, and overlap with ordinary investment conversation such as '价值投资', '长期主义', and '这个创始人怎么样'. This can cause unintended invocation in unrelated contexts, leading the agent to apply a specialized decision framework when the user did not explicitly request it, which may bias outputs or override the expected default behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill is written entirely in Chinese and consistently frames outputs in that language/style without indicating any mechanism to respect the user's preferred language. This can cause usability and comprehension failures, especially if the surrounding system or user operates in another language, increasing the risk of misunderstanding in investment-related analysis.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list includes generic investment phrases such as '价值投资', '长期主义', and founder/moat evaluation prompts that can appear in ordinary financial discussion, making unintended activation likely. Over-broad activation can silently steer responses into a branded framework the user did not request, reducing user control and increasing the chance of irrelevant or biased advice.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The stated auto-activation rule fires whenever users mention broad terms like '高瓴', '张磊', '价值投资', or '长期主义', which are common topical references rather than clear consent to use this skill. This creates ambiguous routing and can cause the system to apply the framework without user intent, leading to misaligned outputs and hidden prompt steering.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The document title and all instructional content are presented exclusively in Chinese, and there is no indication that the user can opt into another language or that the skill is specifically limited to a Chinese-language or region-specific context. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

This markdown file is primarily in Chinese, but line L085 injects the English phrase "fire in the mind" without any indication that mixed-language output is optional or user-selected. Under the language/locale policy rule, forcing or embedding a specific language without opt-in can be a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file presents all user-facing guidance in a single language, which can be a natural-language policy concern when no user opt-in or locale justification is provided. The content does not indicate that the skill is region-specific or that users may choose another language.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file presents all user-facing content in a single language and does not indicate that the language is optional or region-specific. Under the policy rule for natural-language violations, forcing a specific language without user opt-in can be a locale-policy issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file presents all instructional/content text in Chinese and does not provide any indication that the user can choose another language or that the skill is intentionally limited to a Chinese-language audience. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file presents all user-facing content in a single language and does not indicate that Chinese is optional or required for a region-specific purpose. Under the language/locale policy, forcing one language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The natural-language instructions and usage guidance are predominantly Chinese, which effectively forces one language for users reading or invoking the skill. The file does not offer bilingual usage, user language selection, or a stated justification that this skill is intentionally limited to a Chinese-language audience.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file contains user-facing content exclusively in Chinese, and there is no indication that the skill is intended only for Chinese-speaking users or that users may choose another language. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

This markdown file is primarily written in Chinese, but line L010 includes an English quote without any indication that mixed-language output is intentional or optional. Under the language/locale policy rule, forcing or introducing a specific language without user opt-in can be a policy concern, even in descriptive content.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

Lines L059-L062 contain several English-only expressions in a document otherwise targeted at Chinese readers. Because the file does not state that bilingual or English terminology is expected, this may violate language/locale consistency expectations.

Content

No source excerpt is available for this finding.