The Agent Skills Directory

[SAFE]: No security issues detected. The skill consists of a benign Node.js helper script for URL formatting and instructions for using a public web-to-markdown service (markdown.new).
[INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of content from external websites. This represents a potential surface for indirect prompt injection if an attacker-controlled website contains malicious instructions. However, the skill includes explicit policy guardrails instructing the agent to use the service only for public, read-only documentation and articles, and to skip it for authenticated or sensitive workflows.

markdown-url