discover-portal-apis

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

• Third-party content exposure detected (high risk: 0.85). Outsider-authored free text is ingested when the workflow fetches portal asset content—e.g., getTermsAndConditions returns $.content (Markdown/HTML terms authored by the asset publisher) and getAssetPages returns pageContent (documentation pages authored by the asset publisher) which are then placed into the agent’s LLM context.