kegg-database

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 KEGG REST endpoints (e.g., kegg_find, kegg_list, kegg_get, kegg_link) and returns the raw HTTP response text, which is then parsed/used in the agent’s LLM context; this is outsider-authored free text from a public web service (KEGG) fetched at runtime via urllib.request.urlopen(...).read().decode('utf-8').