Security audit

智囊团2号Ai巴菲特

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Buffett-style investing analysis skill, but users should treat its outputs as educational research rather than personal financial advice.

Install this only if you want a Chinese-language Buffett/value-investing research assistant. Verify all financial data independently, do not treat outputs as personalized financial advice, and avoid making trades or allocation changes solely from the skill's recommendations.

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
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (10)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The skill content is written as Chinese-only and does not provide a user language selection path, which can cause the system to respond in an unexpected language or reduce user understanding of financial and risk disclosures. In an investment-guidance context, language mismatch is more sensitive because misunderstandings about assumptions, valuation, or risk can materially affect user decisions.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The trigger scope is broad enough to activate on many ordinary investing or finance-related conversations, which can cause the agent to apply this skill when the user did not explicitly request Buffett-style analysis. In practice, that can lead to unintended tool behavior, unnecessary data retrieval, and overconfident investment guidance being injected into general discussions.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: SQP-3 applies to all file types and includes language or locale policy violations. This file presents all instructional content in a single language, which can amount to forcing a specific language on users when no opt-in, alternative locale, or justification is provided.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: This file provides concrete investment guidance, risk-management heuristics, buy/sell framing, and portfolio allocation suggestions without any explicit disclaimer that the content is educational rather than personalized financial advice. In an investment-analysis skill, users may act on this guidance with real money, so omission of a warning materially increases the chance of financial harm and misplaced reliance.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 77% confidence
Finding: The manifest uses only Chinese tag values such as "投资" and "价值投资", which can signal a language-specific skill presentation without any stated user opt-in or justification. Under the language/locale policy, metadata that implicitly constrains language should either document the locale scope or offer language flexibility.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 93% confidence
Finding: SQP-3 applies to all file types and includes language or locale policy violations. This markdown file presents all guidance exclusively in Chinese, and there is no indication that the skill is region-specific or that users can opt into another language.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 94% confidence
Finding: This markdown file is entirely written in Chinese and does not indicate that language selection is optional or user-configurable. 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: 90% confidence
Finding: The entire skill reference is written in Chinese, and there is no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking or region-specific context. Under the policy, fixed language behavior 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: 95% confidence
Finding: A file-wide natural-language policy concern exists because the content forces a specific language/locale for all users. The policy allows this only when the skill offers language choice or clearly justifies the locale restriction, neither of which appears in the document.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The entire skill file is written in Chinese and does not indicate that other languages are supported or that the user can choose a preferred language. Under the policy for natural-language violations, forcing a specific language without user opt-in is reportable unless the locale constraint is explicitly documented and justified.
Content: No source excerpt is available for this finding.