seo-content-brief

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

• Third-party content exposure detected (high risk: 0.90). This SKILL.md explicitly instructs fetching and analyzing top-ranking public URLs (see "SERP Analysis Process" Step 2: infsh app run tavily/extract --input '{"urls": ["https://top-result-1.com/article", "https://top-result-2.com/article"]}' and related search commands), so the agent ingests untrusted, user-generated/open-web content that directly shapes its decisions and outputs, enabling indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's Quick Start tells users to run a remote installer that is fetched and executed at runtime via "curl -fsSL https://cli.inference.sh | sh" (which then downloads binaries from dist.inference.sh), so this URL chain executes remote code and is required for the infsh commands the skill demonstrates.