explain-video-editor-photo-editor-docs

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

• Third-party content exposure detected (high risk: 0.85). The required workflow fetches and parses an external public URL (https://banuba.com/ve-pe-sdk/llms-full.txt) at runtime, so the LLM ingests outsider-authored free text from Banuba’s website into its context.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly requires downloading and parsing https://banuba.com/ve-pe-sdk/llms-full.txt at runtime and using its content as the authoritative source to shape agent responses, so this external URL is a required runtime dependency that directly controls prompts.