Back to skill

Security audit

Polymarket 预测市场工具

Security checks for vulnerabilities and agentic risk

Overview

This looks like a static Chinese Polymarket guide, but it asks for broad shell and browsing powers while its own README says core functionality is unfinished.

Review this before installing because it grants broad execution and browsing capability despite currently behaving like a static educational guide. Treat it as general information only, not live market data or investment advice, and prefer a version that removes unnecessary tool access or clearly asks before using shell or web browsing.

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 (5)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest claims a functional Polymarket skill with several finance-related capabilities, but the README TODO explicitly says 'implement core functionality' and 'complete documentation', indicating the described behavior is not actually present here. This is a semantic mismatch between the declared skill purpose and the documented implementation status.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file contains user-facing natural language that consistently forces a specific language/locale. Under the policy rules, a language constraint is a violation unless the skill offers opt-in language choice or clearly documents a justified region-specific need, neither of which appears here.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest enables high-risk capabilities (exec, web_search, and browser) even though the skill is described as an informational Polymarket guide with simple query/strategy/risk/returns functionality. This expands the attack surface unnecessarily: shell access in particular could be abused by later prompt content, wrapper scripts, or chained tool invocations to execute unintended commands or retrieve untrusted remote content.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This shell script's user-facing help, guidance, and risk information are all written in Chinese, which effectively forces a specific language for users. The policy allows language constraints only when users are offered a choice or when the locale limitation is clearly documented and justified, neither of which appears here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

Line L03 instructs the author in Chinese ("请在此处填写一句话描述") while the rest of the README structure does not offer any language choice or explain a locale-specific requirement. This creates a natural-language locale constraint without user opt-in or documented justification.

Content

No source excerpt is available for this finding.