video-annotation-review

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

• Third-party content exposure detected (medium risk: 0.30). The workflow reads human review annotations and text prompts from Framebrief, a review surface where external reviewers can submit comments and instructions.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the installation of external packages via npm and npx from third-party repositories without strict version pinning or verification mechanisms, constituting an unverified runtime external dependency.