{"type":"post","id":"cve-2026-119050-agno-pandastools-lets-prompt-injection-219ab1","slug":"cve-2026-119050-agno-pandastools-lets-prompt-injection-219ab1","title":"CVE-2026-119050: Agno PandasTools lets prompt injection call pandas.read_pickle for code execution (CVSS 9.2, no fix released)","description":"VulnCheck has disclosed CVE-2026-119050, a critical unsafe-reflection flaw in Agno's PandasTools through version 3.1.11.","retrieval_nugget":"VulnCheck has disclosed CVE-2026-119050, a critical unsafe-reflection flaw in Agno's PandasTools through version 3.1.11. A prompt injection can influence the pandas function an agent calls, potentially reaching unsafe deserialization or local-file readers. For AI builders, the incident is a concrete warning that tool dispatch must be constrained outside the model's text output.","published_at":"2026-10-30","updated_at":"2026-10-30","record_date":"2026-10-30","date_kind":"published_at","topics":["prompt-injection","agent-security"],"entities":["Agno","PandasTools","pandas","VulnCheck"],"related_patterns":["agent-security-moves-to-runtime-boundaries","agent-ready-software-exposes-capabilities"],"novelty_label":"new_fact","what_changed":"Reports a critical Agno PandasTools unsafe-reflection vulnerability (CVE-2026-119050) enabling prompt-injection-triggered code execution, with no fix released.","prior_refs":[],"source_url":"https://www.vulncheck.com/advisories/agno-through-3.1.11-code-execution-via-pandastools-unsafe-reflection","source_urls":["https://www.vulncheck.com/advisories/agno-through-3.1.11-code-execution-via-pandastools-unsafe-reflection"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:cve-2026-119050-agno-pandastools-lets-prompt-injection-219ab1","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/cve-2026-119050-agno-pandastools-lets-prompt-injection-219ab1/","markdown":"https://newruntime.com/posts/cve-2026-119050-agno-pandastools-lets-prompt-injection-219ab1.md","json":"https://newruntime.com/posts/cve-2026-119050-agno-pandastools-lets-prompt-injection-219ab1.json"},"next_reads":[{"type":"topic","path":"/topics/prompt-injection/","url":"https://newruntime.com/topics/prompt-injection/","title":"Prompt Injection","reason":"Explore the prompt-injection topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/prompt-injection.md","json_url":"https://newruntime.com/topics/prompt-injection.json"},{"type":"topic","path":"/topics/agent-security/","url":"https://newruntime.com/topics/agent-security/","title":"Agent Security","reason":"Explore the agent-security topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/agent-security.md","json_url":"https://newruntime.com/topics/agent-security.json"},{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/source-ledger.json","url":"https://newruntime.com/source-ledger.json","title":"Source Ledger","reason":"Inspect the public source evidence graph.","media_type":"application/json"}]}