seo-schema

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and scans arbitrary page sources (e.g., "Scan page source for JSON-LD <script type="application/ld+json">", and its error handling for "URL unreachable"), so it ingests untrusted public web content that directly influences its analysis and generated actions.

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

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