ClawHub
Back to skill

Security audit

Polymarket Api

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed, read-only Polymarket data wrapper that sends user queries and a ScraperSocial API key only to ScraperSocial's API.

Install only if you are comfortable providing a ScraperSocial API key and sending Polymarket search queries to ScraperSocial. The inspected skill is read-only and does not place trades, but returned odds may be cached and should not be treated as guaranteed live execution prices.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The code clearly targets Polymarket market data through the expected ScraperSocial API family, so the general domain is aligned. However, the declared description says 'prediction market listings and current odds as clean JSON,' which implies a broader or listing-oriented capability and odds retrieval. This script only calls /v1/polymarket/markets with a required query parameter; there is no evidence here of current odds handling. Also, the declared triggers are empty, but the actual code is a command-line script that requires user-supplied input. That makes the description only partially accurate and materially incomplete.

Content

No source excerpt is available for this finding.

Lp1

High
Category
MCP Least Privilege
Confidence
75% confidence
Finding

The skill uses 'env' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.

Content

No source excerpt is available for this finding.

Lp1

High
Category
MCP Least Privilege
Confidence
75% confidence
Finding

The skill uses 'network' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.

Content

No source excerpt is available for this finding.

Lp1

High
Category
MCP Least Privilege
Confidence
75% confidence
Finding

The skill uses 'shell' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.

Content

No source excerpt is available for this finding.

Static analysis

Detected: suspicious.env_credential_access

Environment variable access combined with network send.

Critical
Code
suspicious.env_credential_access
Location
scripts/_client.js:53