ClawHub
Back to skill

Security audit

Prediction Market Sentinel

Security checks for vulnerabilities and agentic risk

Overview

This skill should be reviewed before use because the included monitor ignores the requested wallet address and tracks a hardcoded Polymarket wallet instead.

Review this skill before installing. It does not appear to steal credentials or install persistence, but it does not do what it claims for arbitrary wallet monitoring: the script ignores the wallet address you pass and monitors a fixed address, writes local log/state files, and sends requests to Polymarket's API. Only use it after correcting the hardcoded wallet behavior and documenting the required shell/network/file permissions.

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
  • 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
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill instructs the agent to execute a shell script (`bash scripts/monitor.sh <wallet_address>`) but does not declare any tool scope or permissions in the skill metadata. This creates a governance gap: an agent or reviewer cannot tell from the manifest that shell execution is required, which increases the risk of unintended command execution and makes policy enforcement and auditing harder.

Natural-Language Policy Violations

Low
Confidence
93% confidence
Finding
This shell script contains natural-language comments and runtime log/output messages entirely in Chinese, including the monitoring description and alert text. That imposes a specific language choice on users/operators without offering an alternative or opt-in, which matches the language/locale policy violation criteria.

Static analysis

No suspicious patterns detected.