video-edit

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

• Third-party content exposure detected (low risk: 0.10). The workflow includes fetching creator reels and profile statistics via Apify scrapers or Instagram/Pinterest URLs, which could theoretically process outsider-authored content.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs downloading and running external packages and libraries from CDNs (jsdelivr.net) and remote repositories during runtime without enforced digests or integrity checks, constituting a weak external operational dependency.