seo-hreflang

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

• Third-party content exposure detected (medium risk: 0.65). The skill’s runtime workflow for /seo hreflang audit <directory-or-url> can fetch and parse outsider-authored free text from arbitrary public web pages/URLs (public web content fetched at runtime), which may then be included in the agent’s LLM context for analysis.

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

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