{"data":{"id":"e32f2a69-c66d-4f64-9a68-41504f21f37b","title":"Addressing the OWASP Top 10 Risks in Agentic AI with Microsoft Copilot Studio","summary":"Agentic AI systems (autonomous AI that can retrieve data, invoke tools, and take actions using real permissions) are moving into production, but they introduce unique security risks because failures aren't limited to a single response—they can trigger automated sequences of actions with real-world consequences. The OWASP Top 10 for Agentic Applications (2026) identifies ten key risks in these systems, such as goal hijacking (where an agent's objectives are redirected through injected instructions) and tool misuse (where legitimate tools are exploited through unsafe chaining or ambiguous instructions).","solution":"N/A -- no mitigation discussed in source.","labels":["security","policy"],"sourceUrl":"https://www.microsoft.com/en-us/security/blog/2026/03/30/addressing-the-owasp-top-10-risks-in-agentic-ai-with-microsoft-copilot-studio/","publishedAt":"2026-03-30T16:00:00.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["prompt_injection","model_poisoning","rag_poisoning"],"issueType":"news","affectedPackages":null,"affectedVendors":["Microsoft"],"affectedVendorsRaw":["Microsoft Copilot Studio","Microsoft AI Red Team","OWASP"],"classifierModel":"claude-haiku-4-5-20251001","classifierPromptVersion":"v3","cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"patchAvailable":null,"disclosureDate":"2026-03-30T16:00:00.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["integrity","availability"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.92,"researchCategory":null,"atlasIds":null}}