summarize

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

• Third-party content exposure detected (high risk: 0.90). This skill's SKILL.md explicitly instructs the tool to fetch and extract/read content from arbitrary public URLs (e.g., "telclaude summarize 'https://example.com/article'" and "Articles/blog posts", "YouTube videos", "General web pages"), so untrusted third-party/user-generated content is ingested and interpreted as part of the workflow, enabling indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill fetches and injects arbitrary external URLs at runtime (e.g., "https://example.com/article") to be summarized, which means fetched content directly becomes the model input and can control prompts/instructions.