ClawHub
Back to skill

Security audit

油价查询

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, disclosed oil-price lookup that fetches public data from one API and does not show hidden access, persistence, or destructive behavior.

Before installing, confirm you are comfortable sending requests to the disclosed v2.xxapi.cn oil price API and having curl and jq available. The skill does not require an API key and does not appear to read local files or store data.

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 (1)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill instructs users to execute a local shell script and declares runtime dependencies on curl and jq, but it does not define any explicit tool scope such as permissions or allowed-tools. This creates an avoidable trust gap: a host agent or user may permit shell execution more broadly than necessary, increasing the risk of unintended command execution or abuse if the skill is modified, chained with other skills, or interpreted permissively by the platform.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.