news-media-research

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

• Third-party content exposure detected (low risk: 0.10). The agent uses the Crawlora API to fetch and parse public news articles and headlines from various media outlets, which contain outsider-authored free text.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill references an external commercial API (https://api.crawlora.net/api/v1) as a required operational dependency, but the publisher is an unknown/arbitrary entity lacking strong first-party provenance, making it a high-risk external dependency.