marketing-pipeline-automated-content

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

• Third-party content exposure detected (low risk: 0.10). The skill crawls news articles and social media feeds (TechCrunch, Twitter, LinkedIn) via keyword search and feeds the crawled content into Claude and OpenAI for automated content generation.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill document references a personal GitHub repository (https://github.com/pennydinh/marketing-pineline-share.git) in its installation instructions which is cloned and installed at runtime, constituting a weak/unknown third-party operational dependency.