article-depth-summarizer

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

• Third-party content exposure detected (high risk: 1.00). This skill calls read_url_content to fetch arbitrary user-provided URLs (e.g., "帮我看看这篇... [URL]") and ingests those web pages for analysis, so the agent directly reads and interprets untrusted third‑party content.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill calls read_url_content at runtime to fetch and ingest a user-provided URL (any external URL supplied by the user via read_url_content), and that fetched content is directly injected into the agent's analysis prompts and is required for the skill to operate, so it can control prompts and is flagged.