mcporter

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

• Third-party content exposure detected (high risk: 0.90). The skill (SKILL.md and scripts/mcporter.sh) explicitly calls MCP tools like firecrawl.scrape and chrome-devtools.screenshot with arbitrary URLs and auto-discovers MCP servers, meaning it fetches and ingests untrusted public web content that can influence subsequent tool calls or decisions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill runs "npx --yes mcporter" at runtime (which fetches and executes the 'mcporter' package from the npm registry, e.g. https://registry.npmjs.org/mcporter), meaning required remote code is downloaded and executed during runtime.