markdown-graphs

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The workflow fetches external documentation and examples from https://mdx-graphs.kshv.me/llms.txt, which is an external URL search/fetch rather than a direct monitored feed.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs fetching runtime content (https://mdx-graphs.kshv.me/llms.txt) and installing code (https://mdx-graphs.kshv.me/r/all.json) from an arbitrary unofficial domain, constituting a high-risk external runtime dependency.