iblai-search

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

• Third-party content exposure detected (high risk: 0.75). The skill performs runtime HTTP reads from outsider-authored catalog/mentor content (e.g., GET /dm/api/search/orgs/{org}/users/{username}/mentors/ and GET /dm/api/search/catalog/ return description/data text that is then ingested into the agent’s LLM context), which can include free-form text authored by other users/tenants.