Security audit

A股组合校准

Security checks for vulnerabilities and agentic risk

Overview

This skill organizes user-provided A-share portfolio screenshots or lists into a structured diagnostic packet and does not show hidden execution, persistence, or data exfiltration behavior.

Before using it, redact account numbers, names, broker identifiers, and any other unnecessary personal details from screenshots. Treat its output as portfolio structure analysis, not trading advice or an instruction to buy or sell.

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

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (4)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill explicitly processes sensitive financial information such as portfolio screenshots, holdings, cash balances, and trading constraints, but it provides no privacy notice, minimization guidance, or handling restrictions. This increases the risk that users overshare account data or that downstream components retain or expose personally sensitive financial information beyond what is necessary for portfolio calibration.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: This markdown template is entirely structured in Chinese, including all section headers and field labels, with no indication that the skill is region-specific or that users may choose another language. Under the policy, forcing a specific language without opt-in is 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: 88% confidence
Finding: The natural-language content of the skill is entirely in Chinese, including the description, rules, workflow, and output contract, with no indication that the user can choose another language. This can constitute a language policy violation because it effectively forces a specific language without explicit opt-in or justification.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The default prompt instructs behavior using a mixed-language string and does not indicate that the user can choose their preferred language. Under the policy, forcing or assuming a specific language/locale without opt-in can be a natural-language policy violation unless the locale constraint is explicitly justified.
Content: No source excerpt is available for this finding.