summarize

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

• Third-party content exposure detected (high risk: 0.85). The required workflow ingests outsider-authored free text when the user supplies arbitrary URLs (public web pages) or YouTube links, which the tool fetches/extracts at runtime and then passes into the LLM for summarization (public web content / third-party video transcripts).

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly fetches and summarizes arbitrary external URLs at runtime (e.g., https://example.com and https://youtu.be/dQw4w9WgXcQ), meaning remote content is injected into the model prompt and can directly control instructions.