social-card-gen

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

• Third-party content exposure detected (low risk: 0.10). The required workflow includes fetching content from an arbitrary user-supplied URL via --url, which subjects the agent to outsider-authored free text without pre-selection.

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

• Potentially malicious external URL detected (high risk: 0.70). An operational dependency exists because generate.js fetches content from an arbitrary URL via fetch(options.url) when executed with the --url flag, establishing a weak/unknown runtime dependency.