Security audit

Wenxuecity 24h Rankings

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly matches its stated Wenxuecity ranking purpose, but its script can be directed to fetch arbitrary URLs, which is broader network access than that purpose requires.

Review this before installing if your agent runs in an environment with access to localhost, private networks, or cloud metadata services. The safest change would be to remove or restrict the --url option to the intended Wenxuecity HTTPS host; otherwise only run it where arbitrary outbound HTTP GET requests are acceptable.

A.I.G

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_rankings.py:242
Finding: Unrestricted Source URL Enables Server-Side Request Forgery
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 88% confidence
Finding: The skill invokes a network-fetching script and supports writing output to a file, but the manifest does not declare any explicit tool scope such as permissions or allowed tools. This creates an avoidable trust gap: an agent may execute network and file-write behavior without clear least-privilege boundaries, making review and policy enforcement harder.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 90% confidence
Finding: This markdown file describes fetching rankings from wenxuecity.com, which implies a network request to an external service. The description explains what the skill does, but it does not include any warning or disclosure that running it will contact a third-party website and may transmit system metadata such as IP address or user-agent.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The request hard-codes an Accept-Language header of "zh-CN,zh;q=0.9,en;q=0.7", which imposes a language/locale preference rather than letting the user choose. The policy allows locale constraints only when they are explicitly documented and justified or user-selectable, which is not present here.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.