{"data":{"id":"315e403d-b365-4add-b8c2-c4ba6fd5b4d1","title":"CVE-2026-18733 - Prompt injection bypasses shell tool consent gate in Strands Agents Tools","summary":"Strands Agents Tools, an open-source SDK for building AI agents, has a vulnerability where the shell tool (which runs operating system commands) can be tricked by prompt injection (hiding malicious instructions in text the AI reads) to bypass its human approval requirement. An attacker could craft input that sets a hidden parameter to true, allowing commands to execute on the system without the operator's permission.","solution":"N/A -- no mitigation discussed in source.","labels":["security"],"sourceUrl":"https://aws.amazon.com/security/security-bulletins/rss/2026-072-aws/","publishedAt":"2026-08-03T20:38:42.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"high","attackType":["prompt_injection"],"issueType":"vulnerability","affectedPackages":null,"affectedVendors":[],"affectedVendorsRaw":["Strands Agents"],"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":"2026-08-03T20:38:42.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["integrity","availability"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":null,"atlasIds":null}}