MR-020 Security & adversarial System scope

Insecure integration with external tools, plugins and APIs

Connecting the system to external tools/plugins/APIs introduces injection, data-exfiltration, sandbox-escape, or unintended-action vectors.

Risk family: Security & adversarial
MIT domain: 7. AI System Safety, Failures, & Limitations
MIT subdomain: 7.2 > AI possessing dangerous capabilities
AI type: GPAI, Agentic
Scope: System
Source standard: MIT AI Risk Repository v4

Provenance

Source standard

MIT AI Risk Repository v4

MIT source entries

8 entries across 4 papers

Anwar2024Foundational Challenges in Assuring Alignment and Safety of Large Language Models73.01.00
Cui2024Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems02.06.00 02.06.01
Gipiškis2024Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems62.05.02 62.28.01 62.28.02 62.28.03
Tse2025Frontier AI Risk Management Framework (v1.0)72.06.07

Ev IDs of the entries consolidated into this risk in the MIT AI Risk Repository (V4); the source sheet row appears on hover.

ISO/IEC references

23894 obj A.11; src 9, 10; mech B.6 | 42001 ctrl A.6.2.5, A.10.3

Framework crosswalk

Every framework item mapped to this risk. Items marked partial overlap only in part; definitions appear on hover where the source licence permits.

Sourcesframeworks that contributed to the register

A.11 ISO/IEC 23894 Annex A A.11

A.10.3 ISO/IEC 42001 Annex A A.10.3
A.6.2.5 ISO/IEC 42001 Annex A A.6.2.5

Cross-checksframeworks mapped in to test coverage

ibm-attack-on-ai-agents-external-resources Attack on AI agents' external resources

AISubtech-12.1.1 Parameter Manipulation
AISubtech-12.1.2 Tool Poisoning
AISubtech-12.1.3 Unsafe System / Browser / File Execution
AISubtech-12.1.4 Tool Shadowing

NISTAML.039 Compromising connected resources

LLM05:2025 Improper Output Handling partial
LLM06:2025 Excessive Agency

ASI02 Tool Misuse and Exploitation

More in Security & adversarial

MR-010 MR-012 MR-014 MR-015 MR-016 MR-071

See all Security & adversarial risks →

Part of the Deployer AI Risk Register, an open-source resource powered by MindXO. Version 1.0, 3 July 2026. Derived from the MIT AI Risk Repository (V4, December 2025) under CC BY 4.0; an independent derivative work, not endorsed by or affiliated with MIT. Sub-risk decomposition references MITRE ATLAS™ v5.6.0 (© 2021-2026 The MITRE Corporation, reproduced and distributed with permission). ISO/IEC and EU AI Act references are by number only. License: CC BY 4.0. Full attribution and licensing.