Back to skill

Security audit

China Commodity Quotes

Security checks for vulnerabilities and agentic risk

Overview

This skill is a focused quote-lookup guide for Chinese futures markets and does not show hidden persistence, credential access, or destructive behavior.

Installers should expect this skill to fetch market quote pages from Sina Finance and format results with Chinese futures terminology. It is suitable for quote lookup, not trading execution or financial advice, and users who want non-Chinese output may need to ask the agent to localize labels.

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
  • 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 (1)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The document presents the skill as bilingual in the title, but the usage examples and prescribed output format require Chinese labels such as '实时行情', '最新', and '持仓量' without stating that users may choose another language. This can violate language/locale policy expectations when a skill forces a specific language by default without opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.