Back to skill

Security audit

Cn Url Health Checker

Security checks for vulnerabilities and agentic risk

Overview

This is a simple URL checker, but it can make unrestricted network requests from the agent's environment to any supplied URL.

Install only if you are comfortable letting the agent make outbound URL checks from its runtime environment. Avoid using it on localhost, private-network, cloud metadata, credential-bearing, or untrusted redirecting URLs unless the runtime has network egress controls.

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/url_health.py:5
Finding

Server-Side Request Forgery Through Unrestricted URL Fetching

Content
View full analysis
Remediation
View remediation
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 (4)

Tp4

High
Category
MCP Tool Poisoning
Confidence
89% confidence
Finding

The code generally matches the stated purpose of checking URL health and detecting HTTP/server errors using the Python standard library with no API key. However, the description specifically claims redirect chain detection, while the implementation only reports the final URL after urllib follows redirects automatically. The returned "redirects" field is always an empty list and no redirect history is captured, so that part of the declared behavior is materially overstated.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill advertises and necessarily performs outbound network access but does not declare any explicit tool scope or permissions boundary. This creates a transparency and governance gap: users and hosting systems may not realize the skill can initiate HTTP requests to arbitrary URLs, which increases the risk of misuse such as probing internal services or contacting sensitive endpoints.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The documentation omits a clear warning that the skill makes outbound requests to user-supplied URLs. That omission can lead users to supply untrusted or internal URLs without understanding the privacy and network implications, increasing SSRF-style risk in agent environments where the runtime has broader network reach than the user expects.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The main skill content is in English, but the closing promotional text switches to Chinese and does not provide an opt-in, translation, or explanation that the skill is region-specific. This can violate language/locale policy expectations when a skill implicitly forces or assumes a language without user choice.

Content

No source excerpt is available for this finding.