content-analysis-pro

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

• Third-party content exposure detected (medium risk: 0.65). Outsider free text can enter the LLM context when the operating user provides runtime source material (e.g., uploaded documents/images/video transcripts or pasted text) authored by others; the skill’s pipeline explicitly ingests “Inputs (files, paste, URLs-as-text)” and then performs OCR/ASR/extraction that becomes readable prose for the LLM.