homepage-audit

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

• Third-party content exposure detected (high risk: 1.00). The skill requires and explicitly fetches a live URL using web_fetch (see "Context Loading Gates" in SKILL.md and "If URL provided: web_fetch(URL)" in SKILL-OC.md), meaning it ingests public third-party webpage content that the agent must read and use to drive audit decisions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly calls web_fetch(URL) at runtime to load the user-provided homepage (the provided homepage URL fetched via web_fetch(URL)), and that fetched page content is injected into the agent context to directly drive prompts and audit outputs, so it meets the criteria for a runtime external dependency controlling prompts.