vitest

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

• Third-party content exposure detected (high risk: 0.85). The required workflow uses firecrawl_scrape to fetch https://vitest.dev/llms.txt at runtime, so the agent ingests public web page free-form text (outsider-authored) into the LLM context.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill calls firecrawl_scrape at runtime to fetch LLM-optimized documentation from https://vitest.dev/llms.txt, which is then used to inform/control agent prompts, so this external URL is a runtime dependency that directly controls instructions.