Agentic AI Security & Governance
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 governanceTool governanceControlling what an agent may call, with which authorisations, and leaving an audit trail of what it did. The authorisation question that MCP exposure raises but does not answer.SAP and community, unassessed is named for.
Where it sits
Who is behind it
In the atlas: maintains 146, wrote 61@SAPauthor
Properties
About this work
For tool-governance
Details
Graph
Source
History
- Entered the atlasDiscovered via Added by hand.
For your agent
- Ref
content:btp-ai-bp-agentic-ai-security-governance- JSON
- /content/btp-ai-bp-agentic-ai-security-governance.json
- MCP
- Connecting an agent