harvard-library-catalog

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow calls Harvard’s public LibraryCloud/PRESTO APIs and ingests the returned bibliographic JSON/XML (outsider-authored public web content) into the agent’s LLM context via the script’s parsed fields (e.g., search() → items.json → mods → summarize()), which can include arbitrary text from Harvard records.