scry-vectors

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

• Third-party content exposure detected (high risk: 0.90). The skill issues SQL-over-HTTPS queries against a public corpus (scry.mv_* views such as scry.mv_twitter_threads, scry.mv_blogosphere_posts, scry.mv_arxiv_papers) via /v1/scry/query and returns document text/metadata that the workflows and downstream tools (e.g., scry-rerank/LLM ranking) are expected to read and act on, so untrusted, user-generated third‑party content can materially influence agent decisions.