OWASP Top 10 for Agentic Applications 2026

ASI06 Memory and Context Poisoning

Attackers plant content in an agent's memory or retrieval context so later decisions are corrupted.

OWASP source

Categories that mitigate it

• Runtime guardrails and AI firewalls

Vendors that say they address it

Only vendors that publish their own mapping to this threat are listed.

• LakeraAcquired by Check Point

  Runtime guardrails for LLM applications and agents (Lakera Guard) that screen prompts, tool responses, and tool descriptions for injection and data leakage, plus AI red teaming. Acquired by Check Point in 2025.

  38
• PromptfooBeing acquired by OpenAI

  Open-source red teaming, static scanning, and evaluation for LLM applications and agents, with plugins for tool misuse, MCP, memory poisoning, and prompt injection. OpenAI agreed to acquire it in March 2026 and committed to keep it open source.

  31