firecrawl

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests open/public third-party web content (e.g., SKILL.md commands like "firecrawl search --scrape", "firecrawl scrape """, "map/crawl/browser" which save results to .firecrawl/ and are then read/processed, and the "agent" workflow that extracts structured data), and rules/security.md even warns this fetched web content is untrusted—so third-party pages could indirectly inject instructions that influence agent actions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill's installation step uses npx/npm to fetch and execute the firecrawl-cli package (e.g., https://www.npmjs.com/package/firecrawl-cli), which downloads and runs remote code as a required dependency.