Back to skill

Security audit

ST股票分析

Security checks for vulnerabilities and agentic risk

Overview

The skill is mainly a stock-analysis guide, but it requires saving every report as a PDF to a fixed local folder without asking first.

Review this skill carefully before installing. It appears intended for Chinese ST/*ST stock research and has no bundled executable code, but you should only use it if you are comfortable with it creating PDF reports locally; ideally, modify it to export files only when you explicitly request an export and choose the destination.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill description is written to operate in Chinese and the answering requirements specify a fixed language style, but there is no indication that users may choose another language. Under the policy, fixed language behavior without opt-in or a documented justified regional constraint is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill requires saving every analysis as a PDF under a fixed local path, which introduces filesystem side effects unrelated to the core role of answering stock-analysis questions. Unnecessary file creation can expose local path details, overwrite existing files, or be abused for unwanted artifact generation without explicit user consent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The markdown instructs the agent to save every report as a PDF on the local system without clear user-facing warning or consent. Silent local file creation is dangerous because it creates persistent side effects, may leak sensitive report contents to disk, and violates the principle of least surprise.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

Mandating local file output is not justified by the stated purpose of providing ST stock analysis and expands the skill's effective capabilities beyond analysis into persistent local write operations. This increases risk because a user invoking analysis may not expect local artifacts to be created on their system every time.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.