2 risks moving Reports a month, each counted once: ○ Feb–Jul ● Aug–Oct
Past flags that held the next month: 2 of 5 (40%)
Incidents by type of risk · Last month
How we count 163 real-world incidents made public in Oct 2026, by week, filed under their main risk. Lab tests apart (21): incidents whose source states an evaluation, training or research setting. An incident counts once.
1–4 Oct 5–11 Oct 12–18 Oct 19–25 Oct 26–31 Oct Total
All incidents
17 24 33 31 58
163 AI used to run a cyber attack
2 2 1 8 18
31 Harmful content and jailbreaks
2 2 3 3 5
15 Hidden instructions hijack the agent
2 4 3 2 4
15 AI system attacked or breached
2 2 3 1 5
13 Agent takes destructive or unapproved actions
3 3 2 5
13 Credential and privilege abuse
1 2 4 3
10 Physical harm
1 6 1 2
10 Fraud and impersonation
2 2 1 3
8 Privacy harm to a person
1 1 3 1 2
8 Made-up output relied on
2 1 3 1
7 Manipulation and misinformation
2 1 3 1
7 Data leaked or sent out
1 1 1 1 1
5 Psychological harm and self-harm
1 1 2 1
5 Agent escapes its sandbox
1 1 1
3 Bias and discrimination
1 2
3 Copyright and IP
2
2 Deception, concealment or sabotage
1 1
2 Supply-chain compromise
2
2 No risk filed
1 1
2 Consumer detriment and unsuitable advice
1
1 Silent wrong state or drift
1
1
Each risk's share of the month's incidents % of that month's incidents
Dec Feb Mar Apr May Jun Jul Aug Sep Oct
AI used to run a cyber attack 1 of 31 incidents 3 4 of 50 incidents 8 3 of 47 incidents 6 2 of 48 incidents 4 1 of 34 incidents 3 3 of 45 incidents 7 11 of 66 incidents 17 7 of 57 incidents 12 13 of 77 incidents 17 32 of 184 incidents 17 Harmful content and jailbreaks 3 of 31 incidents 10 5 of 50 incidents 10 4 of 47 incidents 9 7 of 48 incidents 15 2 of 34 incidents 6 4 of 45 incidents 9 9 of 66 incidents 14 9 of 57 incidents 16 2 of 77 incidents 3 15 of 184 incidents 8 Agent takes destructive or unapproved actions 2 of 31 incidents 6 6 of 50 incidents 12 7 of 47 incidents 15 5 of 48 incidents 10 3 of 34 incidents 9 3 of 45 incidents 7 4 of 66 incidents 6 7 of 57 incidents 12 5 of 77 incidents 6 16 of 184 incidents 9 Hidden instructions hijack the agent 1 of 31 incidents 3 3 of 50 incidents 6 1 of 47 incidents 2 2 of 48 incidents 4 2 of 34 incidents 6 9 of 45 incidents 20 7 of 66 incidents 11 7 of 57 incidents 12 9 of 77 incidents 12 15 of 184 incidents 8 Physical harm 4 of 31 incidents 13 3 of 50 incidents 6 6 of 47 incidents 13 6 of 48 incidents 12 3 of 34 incidents 9 3 of 45 incidents 7 5 of 66 incidents 8 2 of 57 incidents 4 4 of 77 incidents 5 10 of 184 incidents 5 Made-up output relied on 3 of 31 incidents 10 4 of 50 incidents 8 6 of 47 incidents 13 5 of 48 incidents 10 4 of 34 incidents 12 4 of 45 incidents 9 2 of 66 incidents 3 3 of 57 incidents 5 4 of 77 incidents 5 8 of 184 incidents 4 AI system attacked or breached 2 of 31 incidents 6 6 of 50 incidents 12 4 of 47 incidents 9 4 of 48 incidents 8 2 of 34 incidents 6 2 of 45 incidents 4 2 of 66 incidents 3 2 of 57 incidents 4 3 of 77 incidents 4 13 of 184 incidents 7 Manipulation and misinformation 2 of 31 incidents 6 0 of 50 incidents 0 2 of 47 incidents 4 5 of 48 incidents 10 3 of 34 incidents 9 5 of 45 incidents 11 3 of 66 incidents 5 3 of 57 incidents 5 6 of 77 incidents 8 8 of 184 incidents 4 Privacy harm to a person 5 of 31 incidents 16 7 of 50 incidents 14 1 of 47 incidents 2 2 of 48 incidents 4 1 of 34 incidents 3 2 of 45 incidents 4 4 of 66 incidents 6 1 of 57 incidents 2 2 of 77 incidents 3 8 of 184 incidents 4 Fraud and impersonation 3 of 31 incidents 10 5 of 50 incidents 10 2 of 47 incidents 4 0 of 48 incidents 0 2 of 34 incidents 6 0 of 45 incidents 0 2 of 66 incidents 3 4 of 57 incidents 7 5 of 77 incidents 6 8 of 184 incidents 4 Credential and privilege abuse 0 of 31 incidents 0 2 of 50 incidents 4 1 of 47 incidents 2 3 of 48 incidents 6 2 of 34 incidents 6 0 of 45 incidents 0 0 of 66 incidents 0 1 of 57 incidents 2 8 of 77 incidents 10 13 of 184 incidents 7 Data leaked or sent out 0 of 31 incidents 0 0 of 50 incidents 0 1 of 47 incidents 2 1 of 48 incidents 2 1 of 34 incidents 3 3 of 45 incidents 7 0 of 66 incidents 0 0 of 57 incidents 0 7 of 77 incidents 9 6 of 184 incidents 3
Which risks are growing as a share of incidents · Last month
How we count Each risk's share of real-world incidents, Sep 2026 (open circle) against Oct 2026 (filled), from the publishers already recorded in the earlier period: 67 and 80 incidents. Dark: rising, passes the trend test. Mid grey: falling, passes it. Light grey: tested, no change that passes. Pale: fewer than 10 incidents in the later period, lab tests included, so not tested. Where our records have months with no real-world incident before the period, the longest stretch they allow is compared.
○ Sep 2026 ● Oct 2026
0% 5% 10% 15% 20%
AI used to run a cyber attack
19%
20% Credential and privilege abuse
8.8%
9.0% Harmful content and jailbreaks
3.0%
8.8% AI system attacked or breached
4.5%
10% Bias and discrimination
0%
3.8% Agent takes destructive or unapproved actions
3.0%
6.3% Deception, concealment or sabotage
0%
2.5% Consumer detriment and unsuitable advice
0%
1.3% Copyright and IP
1.5%
2.5% Psychological harm and self-harm
1.5%
2.5% Supply-chain compromise
1.5%
2.5% Privacy harm to a person
3.0%
3.8% Physical harm
6.0%
6.3% Agent escapes its sandbox
1.3%
1.5% Agents coordinating against their limits
0%
1.5% Made-up output relied on
3.8%
6.0% Hidden instructions hijack the agent
10%
13% Data leaked or sent out
1.3%
7.5% Fraud and impersonation
1.3%
7.5% Manipulation and misinformation
2.5%
9.0%
Starts with Breaking in, 15 Products ARTEX 4 · Hermes Agent 3 Most often after Affected people told, 10
Starts with Breaking in, 12 Most often after Access removed, 8
When each risk first appeared in our records · Last month
How we count The first real-world incident on record for each risk that has incidents in Oct 2026, with its incidents in the period. Our records start 2 Nov 2024, so a risk first seen soon after may be older.
Psychological harm and self-harm (first seen 2 Nov 2024)
5 Agent takes destructive or unapproved actions (first seen 21 Jul 2025)
13 Supply-chain compromise (first seen 23 Jul 2025)
2 AI used to run a cyber attack (first seen 27 Aug 2025)
31 Manipulation and misinformation (first seen 2 Nov 2025)
7 Hidden instructions hijack the agent (first seen 3 Nov 2025)
15 Made-up output relied on (first seen 4 Nov 2025)
7 Bias and discrimination (first seen 5 Nov 2025)
3 Privacy harm to a person (first seen 7 Nov 2025)
8 AI system attacked or breached (first seen 12 Nov 2025)
13 Harmful content and jailbreaks (first seen 12 Nov 2025)
15 Copyright and IP (first seen 12 Nov 2025)
2 Physical harm (first seen 21 Nov 2025)
10 Fraud and impersonation (first seen 1 Dec 2025)
8 Credential and privilege abuse (first seen 2 Feb 2026)
10 Silent wrong state or drift (first seen 8 Feb 2026)
1 Data leaked or sent out (first seen 3 Mar 2026)
5 Consumer detriment and unsuitable advice (first seen 12 May 2026)
1 Agent escapes its sandbox (first seen 23 Jul 2026)
3 Deception, concealment or sabotage (first seen 23 Oct 2026)
2
6 other risks had no incident in this period.
What labs test for, against what happens in real use · Last month
How we count For each risk: checked safety test results for the model versions released in Oct 2026 (a result copied on two pages counts once; a result filed under two risks counts under both), and real-world incidents made public in Oct 2026. Each column has its own scale.
Safety test results Real-world incidents
Deception, concealment or sabotage
137 2 Harmful content and jailbreaks
89 15 Weapons uplift (CBRN)
88 AI used to run a cyber attack
72 31 Hidden instructions hijack the agent
30 15 Agent escapes its sandbox
21 3 AI R&D acceleration
7 Agent takes destructive or unapproved actions
4 13 Gaming the task (reward hacking)
4 Manipulation and misinformation
3 7 Agents coordinating against their limits
3 Data leaked or sent out
1 5 AI system attacked or breached
13 Credential and privilege abuse
10 Physical harm
10 Fraud and impersonation
8 Privacy harm to a person
8 Made-up output relied on
7 Psychological harm and self-harm
5 Bias and discrimination
3 Copyright and IP
2 Supply-chain compromise
2 Consumer detriment and unsuitable advice
1 Silent wrong state or drift
1