jina-cli

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

• Third-party content exposure detected (low risk: 0.10). The skill reads web pages and search results via Jina AI APIs, which constitutes fetching arbitrary external URLs and search content.

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

• Potentially malicious external URL detected (high risk: 0.70). An operational dependency is established via curl execution of an install script from raw.githubusercontent.com and a go install command from github.com, which pull and execute third-party code without strict provenance or integrity guarantees.