seo-ads

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

• Third-party content exposure detected (high risk: 0.85). High likelihood: in domain/keyword modes the skill calls SE Ranking MCP tools (e.g., DATA_getDomainAdsByDomain, DATA_getDomainAdsByKeyword, DATA_getSerpResults) that return third-party scraped SERP/ad copy and URLs (outsider-authored web content) which the workflow then inlines into ADS.md/evidence as readable text for the agent’s LLM context.