placement-exclusion-manager

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

• Third-party content exposure detected (medium risk: 0.65). The skill ingests an exported placements report (user-provided or fetched at runtime) and parses it as untrusted text (“Ingest the placements report — parse where ads served or could serve”), which can contain outsider-authored free text (e.g., scraped page/site/channel descriptions or other publisher-provided text) that becomes LLM-readable context, creating an indirect prompt-injection risk.