author-fs

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow can ingest and render user-supplied source artifacts for the mandatory source-fidelity comparison step (rendering to candidate-review.html and comparing it against the original source), so outsider-authored free text can be included in the “source material” inputs without first selecting a specific item.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill invokes npx -y @sjunepark/fs@0.2.0 (appearing as @sjunepark/fs@0.2.0) in multiple runtime commands, which fetches and executes remote npm package code that the workflow depends on.