{"ref":"content:btp-ai-bp-agentic-ai-security-governance","page":"/content/btp-ai-bp-agentic-ai-security-governance","json":"/content/btp-ai-bp-agentic-ai-security-governance.json","generated":"2026-11-15","drafted_with_ai":true,"entity":{"id":"btp-ai-bp-agentic-ai-security-governance","title":"Agentic AI Security & Governance","url":"https://btp-ai-bp.docs.sap/docs/technical-view/agentic-ai/agentic-ai-security-governance","content_type":"doc","explains":[{"ref":"capability:tool-governance","applies_to":{"ecosystems":["btp"]}}],"offers":["concepts","reference"],"summary":"Names seven threat categories agentic AI introduces beyond ordinary application security: prompt injection, excessive agency, supply-chain and model-integrity compromise, memory poisoning, improper output handling, resource abuse and agent-to-agent communication poisoning. Its answer is a defence-in-depth structure of security controls, input validation, privilege management, supply-chain checks, memory segmentation, output validation, execution quotas, secure communication, paired with governance and oversight: audit logging, explainability, human-in-the-loop review, fairness assessment and continuous monitoring. States the reason plainly: an agent decides, chains actions across turns, keeps memory between them and can act on real systems, a different risk profile from a single request-response call. That is the authorisation and audit-trail question [tool governance](capability:tool-governance) is named for.","short":"Seven threat categories of agentic AI and their governance","authors":["actor:sap"],"sources":[{"url":"https://btp-ai-bp.docs.sap/docs/technical-view/agentic-ai/agentic-ai-security-governance","title":"Agentic AI Security & Governance — SAP BTP AI Best Practices","checked":"2026-09-14","quote":"agentic AI systems introduce a fundamentally different risk profile"}],"provenance":{"discovered_via":[{"source":"source:curator"}],"first_seen":"2026-09-14"},"drafted_with_ai":true,"published_on":"source:btp-ai-best-practices"},"readings":{"liveness":[{"label":"Checked against the source","tier":"unknown","evidence":"nobody has checked it"},{"label":"Source reachable","tier":"unknown","evidence":"not crawled"},{"label":"Age","tier":"unknown","evidence":"no publication date"}],"compatibility":[{"label":"Version","tier":"unknown","evidence":"no version declared"},{"label":"Moved since?","tier":"unknown","evidence":"no publication date to compare"},{"label":"Findings","tier":"good","evidence":"none flagged"}],"reach":[{"value":null,"unit":"views"},{"value":null,"unit":"comments"},{"value":null,"unit":"likes"}]},"signals":null,"series":null,"edges":{"authors":[{"ref":"actor:sap","name":"SAP","json":"/actors/sap.json"}]}}