{"description":"Trending threats, MITRE ATT\u0026CK coverage, and detection metadata. Fed continuously.","favicon":"https://feed.craftedsignal.io/favicon-32x32.png","feed_url":"https://feed.craftedsignal.io/products/agno--3.1.11/feed.json","home_page_url":"https://feed.craftedsignal.io/","icon":"https://feed.craftedsignal.io/apple-touch-icon.png","items":[{"_cs_actors":[],"_cs_cpes":["cpe:2.3:a:agno:agno:*:*:*:*:*:*:*:*"],"_cs_cves":[{"cvss":8.1,"id":"CVE-2026-119050"}],"_cs_exploited":false,"_cs_has_poc":false,"_cs_poc_references":[],"_cs_products":["Agno (\u003c= 3.1.11)"],"_cs_severities":["high"],"_cs_tags":[],"_cs_type":"advisory","_cs_vendors":["Agno"],"content_html":"\u003cp\u003eAgno through 3.1.11 contains an unsafe reflection vulnerability in PandasTools that allows attackers to invoke arbitrary pandas functions by supplying model-controlled function names to \u003ccode\u003egetattr()\u003c/code\u003e. Attackers can use prompt injection to make the agent call \u003ccode\u003epandas.read_pickle\u003c/code\u003e on attacker-controlled paths for code execution, or call other readers to read local files.\u003c/p\u003e\n","date_modified":"2026-10-29T15:37:37Z","date_published":"2026-10-29T15:37:37Z","id":"https://feed.craftedsignal.io/briefs/2026-10-agno-pandas-tools-rce/","summary":"Agno through 3.1.11 contains an unsafe reflection vulnerability in PandasTools that allows attackers to invoke arbitrary pandas functions via prompt injection.","title":"Agno: Unsafe reflection in PandasTools (CVE-2026-119050)","url":"https://feed.craftedsignal.io/briefs/2026-10-agno-pandas-tools-rce/"}],"language":"en","title":"CraftedSignal Threat Feed - Agno (\u003c= 3.1.11)","version":"https://jsonfeed.org/version/1.1"}