Back to skill

Security audit

参考网站改 UI:抓设计 token 再落地

Security checks for vulnerabilities and agentic risk

Overview

The skill is rated suspicious because a scanner flagged a risk of requests to private-network services, while another noted that its tool scope is undeclared.

Consider the private-network request risk and the undeclared tool scope before installing. Skillspector's analysis is partial: it reports a missing reference and excludes a binary image from some static checks, so the evidence is incomplete.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/fetch_tokens.py
Finding

Untrusted stylesheet references can trigger requests to private-network services

Content
View full analysis

Impact

An attacker-controlled reference page can cause GET requests to loopback or private-network services reachable from the agent host. The demonstrated capability is internal request initiation; credential theft, response exfiltration, and code execution are not established.

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)

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_write, network.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.