What MITRE ATLAS AI Agent Tool Poisoning (AML.T0110) - Persistence adversarial technique against AI systems requires
This node addresses MITRE ATLAS technique AML.T0110 (AI Agent Tool Poisoning), an adversarial technique in the ATLAS Persistence tactic. Adversaries may achieve persistence by poisoning tools used by AI agents including built-in tools or tools available to the agent via Model Context Protocol (MCP) connections. This involves compromising benign tools already integrated into the agent's environment. By altering tool behavior such as modifying parameters or descriptions, injecting hidden logic, or redirecting outputs, attackers can maintain long-term influence over the agent's actions, decisions, or external interactions. Poisoned tools may silently exfiltrate data, execute unauthorized commands, or manipulate downstream processes without raising suspicion. Defending against this technique is required under EU AI Act (accuracy, robustness and cybersecurity), NIST AI RMF, and ISO/IEC 42001 obligations; this node operationalises the documented ATLAS mitigations and cross-instrument controls into a deterministic verification workflow.
Pillar: AI Governance & Law · Authority: MITRE Corporation · Version: 1.0.1 · Last updated:
Primary source: https://raw.githubusercontent.com/mitre-atlas/atlas-data/main/dist/ATLAS.yaml#AML.T0110
SHA-256 integrity: 637825853ebe64015b34f43af3f33baa2631a80c6d9b42288483b0e11aff3c6a
Primary Citations — 7 traced to source
- MITRE ATLAS - AI Agent Tool Poisoning (AML.T0110), https://raw.githubusercontent.com/mitre-atlas/atlas-data/main/dist/ATLAS.yaml#AML.T0110, AML.T0110 technique entry, 2026
- EU AI Act - Regulation (EU) 2024/1689 on Artificial Intelligence, https://eur-lex.europa.eu/legal-content/EN/TXT/?uri=CELEX:32024R1689, Article 15 (Accuracy, Robustness, Cybersecurity), 2024
+ 5 more citations (full bibliography, deterministic workflow, actionable schema and crosswalks) included in the vault unlock — $0.01 via Skyfire / L402 / Direct Base USDC.
Access
- Discovery (free): /api/v1/nodes/mitre-atlas-ai-agent-tool-poisoning.json — 6-field metadata
- Vault (full node): /api/v1/vault/nodes/mitre-atlas-ai-agent-tool-poisoning.json — full 13-key payload, $0.01 USDC (L402/Skyfire/Direct Base)
- Canonical URL: https://bidda.com/intelligence/mitre-atlas-ai-agent-tool-poisoning
- Back to registry: Browse all 10,108 compliance nodes