{"data":{"id":"01e9d33a-963e-43f4-b4a6-3a42ddedaccf","title":"datasette-llm 0.1a5","summary":"datasette-llm 0.1a5 is a release of a plugin that lets other software tools integrate with large language models. The update improves the llm_prompt_context() plugin hook (a mechanism that other plugins can connect to), so it now tracks both individual prompts and chains of prompts executed together, including tool call loops (repeated back-and-forth exchanges between the AI and external functions).","solution":"N/A -- no mitigation discussed in source.","labels":["industry"],"sourceUrl":"https://simonwillison.net/2026/Apr/1/datasette-llm/#atom-everything","publishedAt":"2026-04-01T03:11:01.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"news","affectedPackages":null,"affectedVendors":[],"affectedVendorsRaw":["datasette-llm"],"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":"2026-04-01T03:11:01.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":null,"aiComponentTargeted":"framework","llmSpecific":true,"classifierConfidence":0.75,"researchCategory":null,"atlasIds":null}}