seo

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

• Third-party content exposure detected (high risk: 1.00). The skill's agents explicitly fetch and analyze open web content (e.g., crawl-agent reads robots.txt/sitemaps and site pages; ai-presence-agent checks third-party profiles like G2/Capterra/Wikipedia/YouTube and runs live queries across ChatGPT/Perplexity/Google AI), which are untrusted, user-generated or public sources and are used to drive decisions and actions in the workflow (see SKILL.md and agents/ai-presence-agent.md), so it clearly exposes the agent to indirect prompt injection risk.