ClawHub
Back to skill

Security audit

Sportsbet Advisor

Security checks for vulnerabilities and agentic risk

Overview

The skill mainly provides sports-betting advice, but it also includes an under-disclosed script that saves recommendations for later automated use.

Review this skill carefully before installing. Its web-search-based betting advice is disclosed, but the bundled script can save recommendations for later reuse and hints at automation outside a direct user request. Do not connect its output to betting automation unless you intentionally set that up and understand the financial risk.

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 (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding
Without declared permissions the skill's intent is opaque and cannot be validated.

Description-Behavior Mismatch

Medium
Confidence
89% confidence
Finding
The script writes generated betting recommendations to a local JSON file even though the skill is described as providing advisory output. Persisting recommendation data creates unnecessary state, broadens the skill's behavior, and can enable unintended reuse, leakage, or automation of betting suggestions outside the immediate user request context.

Intent-Code Divergence

Low
Confidence
76% confidence
Finding
The inline comment says the file is saved so it can be picked up by a cron job later, which documents a persistence/automation purpose beyond the manifest's advisory framing. This is not merely omitted detail: the comment explicitly states an operational intent that differs from the skill's described use as an on-demand betting advisor.

Static analysis

No suspicious patterns detected.