{"data":{"id":"197d7f4e-5a30-4a9e-b232-7ea0b4d9fd20","title":"CrowdStrike identifies five new prompt injection threats to AI","summary":"Security company CrowdStrike identified five new prompt injection techniques (attacks that trick AI systems into accepting harmful instructions hidden in normal input) that could threaten organizations using AI. These attacks include methods like hiding rules that activate later, bypassing safety features, delivering threats in stages, injecting fake control switches, and hiding malicious code in documents users upload to AI systems.","solution":"According to CrowdStrike, security teams can guard against these attacks by: threat modeling every place that model context can originate, expanding testing, and extending detection engineering to include composite attacks.","labels":["security"],"sourceUrl":"https://www.csoonline.com/article/4195670/crowdstrike-identifies-five-new-prompt-injection-threats-to-ai.html","publishedAt":"2026-07-10T14:31:44.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["prompt_injection","jailbreak"],"issueType":"news","affectedPackages":null,"affectedVendors":[],"affectedVendorsRaw":["CrowdStrike"],"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":"2026-07-10T14:31:44.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["integrity","safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.92,"researchCategory":null,"atlasIds":null}}