homepage-audit

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

• Third-party content exposure detected (high risk: 0.90). This skill's Context Loading Gates explicitly require a live URL and state "fetch with web_fetch if available," meaning the agent will retrieve and read arbitrary public webpages (untrusted third-party content) and use that content to drive scoring and rewrite/recommendation actions, creating a clear indirect prompt-injection risk.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill requires fetching a user-provided live URL at runtime (via web_fetch) and uses the fetched page content to directly drive the audit prompts/instructions, so the "user-provided live URL (fetched via web_fetch)" is a runtime external dependency that can control the agent.