newsletter-topic-landscape

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

• Third-party content exposure detected (low risk: 0.10). The workflow queries public Substack newsletters, posts, and search results via Crawlora API endpoints, ingesting outsider-authored article titles, summaries, and post content.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill executes runtime calls to Crawlora API endpoints via scripts/crawlora.sh using an unknown third-party publisher provenance, constituting a medium-tier operational dependency.