create-title

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

• Third-party content exposure detected (high risk: 0.90). The skill's mandatory Step 2 ("Research the Niche") requires performing WebSearch queries and using WebFetch on top public URLs (extracting title examples from "top creators" and other web pages) — i.e., it ingests untrusted, user-generated/open web content and uses those findings to directly shape title-generation decisions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly requires runtime WebFetch of the "top 1-2 most relevant URLs" from WebSearch — i.e., arbitrary external web pages fetched at runtime whose extracted content is injected into the agent's prompt/research context and thus can directly control outputs (no specific fixed URL is provided, but the runtime-fetched external URLs are a required dependency).