seo-content-writer

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

• Third-party content exposure detected (high risk: 0.90). The skill's Data Sources and Research steps explicitly require automatically pulling competitor content analysis and SERP features from external top-ranking pages ("With ~~SEO tool + ~~search console connected: Automatically pull ... competitor content analysis (top-ranking pages, content length, common topics)" and the "SERP Analysis" item in step 3), so the agent would ingest and act on untrusted public web content that can change its outputs and actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly instructs the agent to "load content quality standards from the CORE-EEAT Benchmark" at https://github.com/aaron-he-zhu/seo-geo-claude-skills/blob/main/references/core-eeat-benchmark.md, which indicates a runtime fetch of remote Markdown that directly controls prompts/instructions for writing content.