{"type":"post","id":"crowdstrike-expands-its-prompt-injection-taxonomy-to-222-3a0771","slug":"crowdstrike-expands-its-prompt-injection-taxonomy-to-222-3a0771","title":"CrowdStrike expands its Prompt Injection Taxonomy to 222 techniques, adding attacks on agent planning","description":"CrowdStrike has expanded its public Prompt Injection Taxonomy to 222 techniques, adding attacks intended to influence how autonomous agents plan, select tools, and interpret session history.","retrieval_nugget":"CrowdStrike has expanded its public Prompt Injection Taxonomy to 222 techniques, adding attacks intended to influence how autonomous agents plan, select tools, and interpret session history. For teams building agents, the change is a reminder that harmful behavior can emerge from a plausible sequence of individually ordinary steps, not only from an obvious malicious prompt.","published_at":"2026-10-30","updated_at":"2026-10-30","record_date":"2026-10-30","date_kind":"published_at","topics":["prompt-injection"],"entities":["CrowdStrike","CrowdStrike Prompt Injection Taxonomy","Falcon Guardian","Vanessa Villa","Jim Hoagland"],"related_patterns":["agent-security-moves-to-runtime-boundaries","harness-architecture-outlives-model-choice"],"novelty_label":"new_fact","what_changed":"CrowdStrike’s taxonomy now covers 222 prompt-injection techniques, including attacks targeting agent planning.","prior_refs":["memory:f7b819cf-62b9-8880-ad27-6efc1bc20f11"],"source_url":"https://www.crowdstrike.com/en-us/blog/new-prompt-injection-techniques-cover-agent-planning-attacks","source_urls":["https://www.crowdstrike.com/en-us/blog/new-prompt-injection-techniques-cover-agent-planning-attacks"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:crowdstrike-expands-its-prompt-injection-taxonomy-to-222-3a0771","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/crowdstrike-expands-its-prompt-injection-taxonomy-to-222-3a0771/","markdown":"https://newruntime.com/posts/crowdstrike-expands-its-prompt-injection-taxonomy-to-222-3a0771.md","json":"https://newruntime.com/posts/crowdstrike-expands-its-prompt-injection-taxonomy-to-222-3a0771.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":"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"}]}