Security audit

Web to Markdown

Security checks for vulnerabilities and agentic risk

Overview

The skill has a coherent URL-to-markdown purpose, but its shell-command examples can execute unsafe user-supplied URL text and it forwards complete URLs to third-party services without enough user-side safeguards.

Install only if you are comfortable having supplied URLs sent to markdown.new or r.jina.ai. Do not use it for private intranet pages, localhost URLs, signed download links, password-reset or invite links, or URLs containing access tokens unless the skill is revised to validate URLs and avoid shell-string interpolation.

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 (2)

T09 · Insecure Skill Coding Practices

Error

Location: SKILL.md:36
Finding: Shell Command Injection Through Untrusted URL Interpolation
Content: View full analysis
Remediation: View remediation

other

Warning

Location: SKILL.md:36
Finding: Disclosure of Complete User-Provided URLs to Third-Party Extraction Services
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill instructs the agent to send user-provided URLs to third-party services (markdown.new and r.jina.ai) but does not require any user-facing disclosure or consent before doing so. URLs can contain sensitive query parameters, private document links, internal hostnames, or access tokens, so forwarding them to external services can leak confidential information and browsing intent.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.