seo-schema

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

• Third-party content exposure detected (high risk: 0.70). The skill’s required workflow is to scan a page’s source for JSON-LD/Microdata/RDFa and validate it; if the page content is fetched from a user-supplied URL at runtime, that fetched outsider-authored page text/markup is ingested into the LLM context for analysis (public web content path: runtime URL fetch → page source/markup → LLM).

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

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