ai-content-pipeline

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

• Third-party content exposure detected (low risk: 0.10). The skill documentation describes composing pipelines with specific apps (e.g., openrouter/claude-*, tavily/search-assistant) via belt app run, and does not indicate the required runtime workflow passively monitors or continuously ingests outsider-authored free text (it only uses first-party/trusted model inputs you provide in --input or content returned by a named search tool, which is not shown as a queue/feed ingestion path).