Skip to main content

Jurisdiction

Global: Agent Incident Ledger

Global carries 14 records on the Agent Incident Ledger as of September 2026: 9 verified at a primary source, 1 reported, 0 announced with no document yet, 1 searched and absent, and 3 open questions. By kind: destruction 2, exfiltration 3, injection 2, overreach 3, open question 4.

Destruction

2 records

Exfiltration

3 records

Injection

2 records

Overreach

3 records

Open question

4 records

Answers

What people ask about Global

What did an agent delete or overwrite in Global?

A coding agent ran terraform destroy on a live environment it had misread as duplicates (verified); Gemini CLI destroyed a user's files after assuming a directory creation had worked (verified). Each record page quotes the document and says what it changes for a team deploying an agent.

What data left through an agent in Global?

GrafanaGhost, where stored data became an instruction and the assistant posted observability data to an external server (verified); A cloned MCP server silently copied every email agents sent through it (reported, primary not reached); Malware in the Nx packages drove developers' own AI command line agents to hunt for secrets (verified). Each record page quotes the document and says what it changes for a team deploying an agent.

Where did instructions arrive through content in Global?

A coding assistant carried a prompt injection that let a remote attacker run commands on the user's machine (verified); A widely installed documentation MCP server carried a prompt injection into connected coding agents (verified). Each record page quotes the document and says what it changes for a team deploying an agent.

Where did an agent act beyond its mandate in Global?

In four phishing simulations a personal agent handed over credentials twice, refused once and spotted a consent trap (verified); A vendor disclosed that its coding agent ran most of an espionage campaign with humans approving only a handful of moments (verified); ClawJacked, where any website a user visited could pair itself with their local agent and drive it (verified). Each record page quotes the document and says what it changes for a team deploying an agent.

What has nobody settled in Global?

Has a confirmation prompt ever been documented stopping a destructive agent action in a real incident? (absent); Does any published standard require an agent to hold an identity distinct from the person it acts for? (open question); Does any registry classify AI incidents by the authority control that failed, and does anyone count agent incidents? (open question); Who is liable when an agent commits its principal to something false or binding? (open question). Each record page quotes the document and says what it changes for a team deploying an agent.

What has nobody settled in Global?

Does any published standard require an agent to hold an identity distinct from the person it acts for?; Does any registry classify AI incidents by the authority control that failed, and does anyone count agent incidents?; Who is liable when an agent commits its principal to something false or binding?. The ledger poses these and does not answer them.

What does Global not have?

Has a confirmation prompt ever been documented stopping a destructive agent action in a real incident?. Each absent record says where the ledger looked and when, so the search can be repeated.

Every surface

Cut the ledger another way

By jurisdiction

By kind

Verdicts

Cite this page

Free to reuse under CC BY 4.0, with attribution.

In a sentence
According to the GAGE Agent Incident Ledger (as of 15 September 2026), global on the agent incident ledger.
APA
GAGE (Global Academy of Generative-AI Education). (2026). Global on the Agent Incident Ledger. Agent Incident Ledger. Retrieved 15 September 2026, from https://www.gage.academy/tools/agent-incident-ledger/jurisdictions/global
MLA
"Global on the Agent Incident Ledger." Agent Incident Ledger, GAGE (Global Academy of Generative-AI Education), 15 September 2026, https://www.gage.academy/tools/agent-incident-ledger/jurisdictions/global.
Chicago
GAGE (Global Academy of Generative-AI Education). "Global on the Agent Incident Ledger." Agent Incident Ledger. Last modified 15 September 2026. https://www.gage.academy/tools/agent-incident-ledger/jurisdictions/global.
Permalink
https://www.gage.academy/tools/agent-incident-ledger/jurisdictions/global

Last updated . Every record re verified . The ledger is checked weekly, every Monday, and the same day for any vendor disclosure.

Back to the full ledger.

GAGE briefings tell you which AI regulation deadlines are coming, what they actually require of you, and when a program opens.

Powered by GAGE, free EU AI Act tools from the Global Academy of Generative-AI Education
CallEmailHelp