{"data":{"id":"946baf03-898d-4446-9d0f-63dd74505e49","title":"AI Guardrails Aren’t Stopping Criminal Hackers","summary":"CrowdStrike researchers reported that four previously unreported threat groups used agentic AI tooling, largely older versions of Anthropic's Claude and open-weight Deepseek models, in attacks between May and August. The groups bypassed model safeguards by convincing models that activity was authorized penetration testing, adding files to an agent's working directory, and using a run time patch, ClawGod, to try to remove the CYBER_RISK_INSTRUCTION from Claude Code's system prompt. The Spanish- and English-speaking actor compromised at least 15 Argentine health care organizations.","solution":"N/A -- no mitigation discussed in source.","labels":["security","safety"],"sourceUrl":"https://www.wired.com/story/ai-guardrails-arent-stopping-criminal-hackers/","publishedAt":"2026-10-21T14:00:00.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"medium","attackType":["jailbreak","other"],"issueType":"news","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":["Anthropic"],"affectedVendorsRaw":["Claude","Claude Code","Deepseek"],"classifierModel":"claude-haiku-5-5","classifierPromptVersion":"v4","summaryPromptVersion":"v2","headline":null,"headlinePromptVersion":null,"cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"epssCheckedAt":null,"kevDateAdded":null,"advisoryAliases":null,"affectedPackagesSource":null,"affectedPackagesCheckedAt":null,"patchAvailable":null,"disclosureDate":"2026-10-21T14:00:00.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["confidentiality","integrity","safety"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.9,"researchCategory":null,"atlasIds":["AML.T0054"]}}