bilibili-portfolio-search

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

• Third-party content exposure detected (low risk: 0.10). Required runtime workflow (references/core_workflow.md Step 2) ingests outsider-authored free text only indirectly via the user-provided UID/cursor and then renders first-party API-derived video titles/names from the fetched UP’s public works; it does not monitor a queue/feed where outsiders can post arbitrary text for the agent to consume without selecting a specific UID.