marketing-pipeline-share-automation

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow includes an “Auto-Research” step that crawls/scrapes external news sources (e.g., TechCrunch, Twitter, LinkedIn) and extracts article text/insights, which is then fed into the LLM context for AI content generation (indirect prompt injection risk from outsider-authored web content).

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's research module/scraper fetches external pages at runtime (e.g., the example custom source URL "https://example.com/blog" and sources like TechCrunch/Twitter/LinkedIn) and the scraped content is injected into the AI generation prompts (research.insights), so remote content can directly control the model's prompts.