technical-seo-checker

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime workflow includes fetching and embedding third-party site content such as /robots.txt and XML sitemap contents (and likely other crawled page text) into the LLM context, which is outsider-authored free text from the target domain.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)