mermint-markdown-workflow

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

• Third-party content exposure detected (high risk: 0.80). The skill's workflow explicitly requires fetching and running the mermint CLI from a public GitHub repo (see the npx git+https://github.com/alessandrobologna/mermint.git command in SKILL.md), which is untrusted third-party content that the agent will ingest/execute as part of its processing and can therefore materially alter behavior.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill's runtime commands use npx to fetch and execute remote code from git+https://github.com/alessandrobologna/mermint.git, making that URL a required runtime dependency that executes external code.