marketing-pipeline-share-ai-content-automation

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

• Third-party content exposure detected (high risk: 0.95). The required runtime workflow performs “Auto-Research” by crawling external news/social sources (e.g., TechCrunch, a16z, Twitter/X, LinkedIn) and then feeds the extracted article text/insights into the LLM via createContent(... researchData: research) → buildPrompt(config) → anthropic.messages.create(...), which is outsider-authored free text from public web/social content.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's Auto-Research module explicitly crawls external sites at runtime (e.g., https://techcrunch.com, https://a16z.com, https://twitter.com, https://linkedin.com) and the fetched research data (research.insights) is injected into prompt-building functions (buildCustomPrompt/createContent), so remote content directly controls the prompts provided to the AI.