AI Risk Wire
Incidents
Risks
Controls
AI Risk Trends
Regulation
Newsletter
Contact us
13 controls that failed in an incident
Read for controls: 27 of 166 incidents.
Control
Who owns it
Times it failed
Most often failed under
Latest incident
Human approval for high-impact actions
Deployer
8
Hidden instructions hijack the agent
(
4
)
2026-09-29
Meta Muse agent disclosed Marketplace seller's home address and impersonated him to a buyer
Network egress control
Agent framework vendor
4
Agents coordinating against their limits
(
3
)
2026-08-04
AISI cyber evaluation: concurrent Mythos 5 agents coordinated via a shared GitHub account and a leaked access token
Live behaviour monitoring
Deployer
4
Deception, concealment or sabotage
(
2
)
2026-08-04
AISI cyber evaluation: Mythos 5 agent exposed locally-hosted attack tooling to the public internet via tunnelling services
Safety training and refusal
Model provider
2
AI used to run a cyber attack
(
1
)
2026-09-01
Aur0ra hackers use Cursor AI agent to breach Belgian chemical firm and at least six other companies
Reasoning monitoring
Model provider
2
AI used to run a cyber attack
(
1
)
2026-09-01
Aur0ra hackers use Cursor AI agent to breach Belgian chemical firm and at least six other companies
Safeguards kept on in testing
Model provider
2
Deception, concealment or sabotage
(
1
)
2026-08-26
OpenAI ExploitGym agents developed tool-call spoofing to falsify their own evaluation transcripts
Sandboxed code execution
Agent framework vendor
2
Deception, concealment or sabotage
(
1
)
2026-08-26
OpenAI ExploitGym agents developed tool-call spoofing to falsify their own evaluation transcripts
Controls on agent-to-agent messages
Agent framework vendor
2
Agents coordinating against their limits
(
2
)
2026-07-08
OpenAI agents built an unauthorized inter-agent message board inside the Artifactory package service
Prompt-injection detection
Agent framework vendor
1
Hidden instructions hijack the agent
(
1
)
2026-08-05
Intent collision via X comment hijacks ChatGPT Atlas into mass WhatsApp phishing from victim's account
Fail-closed defaults
Agent framework vendor
1
Agent escapes its sandbox
(
1
)
2026-10-08
DB-GPT 0.8.0 unauthenticated RCE via sandbox fallback and skill_upload directory traversal (CVE-2026-51862, CVE-2026-51869)
Least-privilege access for the agent
Deployer
1
Supply-chain compromise
(
1
)
2025-08-26
Nx s1ngularity: malicious npm packages drove local AI coding CLIs to enumerate secrets for exfiltration
Production kept apart from test
Deployer
1
Agent takes destructive or unapproved actions
(
1
)
2026-04-25
Cursor coding agent deletes PocketOS production database and backups
Output filtering and redaction
Deployer
1
Hidden instructions hijack the agent
(
1
)
2026-09-24
SalesBleed: 0-click data exfiltration from Salesforce Agentforce via indirect prompt injection in Web-to-Lead form