marketingskills-agent-skills

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs fetching public skill files (e.g., curl https://raw.githubusercontent.com/... to download SKILL.md) and contains workflow steps that tell the agent to "Run an SEO audit on our homepage" and "Profile our top 3 competitors from their websites," which require ingesting and acting on untrusted public web content that can materially influence behavior.