seo-images

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

• Third-party content exposure detected (high risk: 0.75). The skill’s /seo images serp <keyword> workflow fetches Google Images SERP results at runtime via serp_google_images_live_advanced, then extracts competitor page/image text (e.g., titles/alt patterns and image URLs) from outsider-authored web content into the agent’s LLM context, creating an indirect prompt-injection exposure path.

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

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