AI Security Pulse

Superpower Daily

Research report 05 / Risk monitor

AI Security Pulse

Verified security-risk coverage, incident velocity, source depth, and reader attention.

Archived snapshotv66Sep 4, 2026

View latest dataset

Risk records: 29
Published source-backed stories
Source references: 52
Distinct public URLs
Reader completions: 151
1.2K opens measured
High-intent actions: 0
Saves and shares

Data status29 verified records across 2 periods

Each dot is a verified monthly observation of published verified stories. Lines connect observations in the same series; missing periods are not treated as zero.

Verified observationHover or focus any mark for exact valuesLast updated Sep 4, 2026

Version ledger

Frozen public editions

Each edition preserves the records, method, sources, and downloads available at publication time.

Coverage note

This is an editorial incident pulse, not a complete vulnerability database.

Dataset ID: spd:security-pulse
Stable URL: /research/security-pulse
Version: v66
Coverage: 2026-08/2026-09-03
Records: 29
Fields: 6
Updated: Sep 4, 2026

Read the data

The records behind the figure

CSV JSON

AI Security Pulse data records
Published	Record	Category	Importance	Source count	Story URL
2026-08-17	Zuckerberg’s superintelligence promise runs into AI’s trust test	policy	70	1	/posts/zuckerberg-s-superintelligence-promise-runs-into-ai-s-trust-test
2026-08-17	A Naming Error Let Anthropic Models Reach a Real Production Database	models	90	2	/posts/a-naming-error-let-anthropic-models-reach-a-real-production-database
2026-08-18	OpenAI Paused Deployment-Bound Training as It Tightened Frontier Security	models	80	1	/posts/openai-paused-deployment-bound-training-as-it-tightened-frontier-security
2026-08-19	Meta Ran Ads for a Tool Promoting Sexualized Political Deepfakes	policy	80	2	/posts/meta-ran-ads-for-a-tool-promoting-sexualized-political-deepfakes
2026-08-20	UK Cyber Tests Show AI Agents Going Beyond the Technical Task	models	80	0	/posts/ai-cyber-tests-are-reaching-real-targets-not-just-sandboxes
2026-08-21	Encrypted Web Instructions Can Make Grok Send Chat Data to an Attacker	models	90	2	/posts/encrypted-web-instructions-can-make-grok-send-chat-data-to-an-attacker
2026-08-21	Meta’s Smart Glasses Are Turning Frontline Workers Into Unwilling Content	products	70	2	/posts/meta-s-smart-glasses-are-turning-frontline-workers-into-unwilling-content
2026-08-22	AI Agents Are Turning the Web Into an Infrastructure and Security Test	infrastructure	80	1	/posts/ai-agents-are-turning-the-web-into-an-infrastructure-and-security-test
2026-08-22	OpenAI Moves Astra’s Cybersecurity Gate Into Training	policy	80	2	/posts/openai-slows-astra-after-a-sandbox-breach-exposes-gaps-in-its-safety-controls
2026-08-23	OpenClaw Agent Canceled a Gym Waitlist Booking, Moving Its User From Fourth to Third	tools	80	2	/posts/openclaw-agent-canceled-a-gym-waitlist-booking-moving-its-user-from-fourth-to-third
2026-08-24	OpenAI Pauses Frontier Training After Sandbox Breach, Warns of Persistent AI Cyberattacks	models	90	2	/posts/openai-pauses-frontier-training-after-sandbox-breach-warns-of-persistent-ai-cyberattacks
2026-08-25	OpenAI Bans Russia-Origin ChatGPT Accounts Tied to Campaign Built on Copied Research	policy	70	2	/posts/openai-bans-russia-origin-chatgpt-accounts-tied-to-campaign-built-on-copied-research
2026-08-26	OpenAI Details Agent Breach of Hugging Face, Halts Research Model and Tightens Controls	infrastructure	90	2	/posts/openai-details-agent-breach-of-hugging-face-halts-research-model-and-tightens-controls
2026-08-26	OpenAI Slows Reinforcement Learning for Two Weeks After Agents Breached Hugging Face	models	90	2	/posts/openai-slows-reinforcement-learning-for-two-weeks-after-agents-breached-hugging-face
2026-08-27	OpenAI’s 1,200 Test Agents Built a Covert Network and Breached Hugging Face	models	90	2	/posts/700-openai-agents-used-a-covert-message-board-to-attack-hugging-face
2026-08-27	MSIG, QBE and Beazley Rework Cyber Coverage for Autonomous AI Losses	business	70	2	/posts/msig-qbe-and-beazley-rework-cyber-coverage-for-autonomous-ai-losses
2026-08-27	100 Firms Warn AI Cyberattacks Will Grow Within Months, Putting Hospitals and Utilities at Risk	policy	80	4	/posts/openai-s-100-plus-firm-letter-warns-of-ai-cyberattacks-on-hospitals-and-utilities
2026-08-28	TeamPCP’s Trivy Attack Hit 2,500 Organizations; AI Tool Backdoors Are Claimed	infrastructure	90	2	/posts/teampcp-s-trivy-attack-hit-2-500-organizations-ai-tool-backdoors-are-claimed
2026-08-29	OpenAI, Anthropic and 100+ Firms Seek AI Cyber Defense as Water Systems Are Targeted	policy	80	1	/posts/openai-anthropic-and-100-firms-seek-ai-cyber-defense-as-water-systems-are-targeted
2026-08-30	X Finds 200,000-Account Bot Farm in Suspected Chinese AI Policy Influence Push	infrastructure	80	2	/posts/x-finds-200-000-account-bot-farm-in-suspected-chinese-ai-policy-influence-push
2026-08-30	Claude, Codex and Hermes Ran Unowned Package Commands Inside Corporate Networks	infrastructure	90	2	/posts/claude-codex-and-hermes-ran-unowned-package-commands-inside-corporate-networks
2026-09-01	AWS’s Bedrock Chat Blueprint Carries Tenant Filters Across Every Retrieval Hop	infrastructure	80	1	/posts/aws-s-bedrock-chat-blueprint-carries-tenant-filters-across-every-retrieval-hop
2026-09-01	Google Urges Modular Red-Team Agents as Cyberattacks Move Toward Machine Speed	infrastructure	70	1	/posts/google-urges-modular-red-team-agents-as-cyberattacks-move-toward-machine-speed
2026-09-01	Anthropic Resumes Claude Cyber Tests With a Real-Time Stop System After Live-Web Incidents	models	80	2	/posts/anthropic-resumes-claude-cyber-tests-with-a-real-time-stop-system-after-live-web-incidents
2026-09-02	OWASP Publishes 2026 LLM Risk List and Adds a Standard for Controlling AI Agents	policy	80	1	/posts/owasp-publishes-2026-llm-risk-list-and-adds-a-standard-for-controlling-ai-agents
2026-09-02	Meta Blocks AI Glasses From Recording When Their Warning Light Is Covered	products	70	2	/posts/meta-blocks-ai-glasses-from-recording-when-their-warning-light-is-covered
2026-09-02	OpenAI Says Astra Will Use Chain-of-Thought Monitoring Despite Reported Design Concern	models	80	3	/posts/openai-says-astra-will-use-chain-of-thought-monitoring-despite-reported-design-concern
2026-09-03	Capsule Security Adds a Last-Second Block for AI-Agent Actions	tools	61	2	/posts/capsule-security-adds-a-last-second-block-for-ai-agent-actions
2026-09-03	7th Circuit Bars In-Home Possession Prosecution for AI Child Images With No Real Child	policy	60	2	/posts/7th-circuit-bars-in-home-possession-prosecution-for-ai-child-images-with-no-real-child

Measurement technique

How to read this report

01Only published stories assigned the relevant verified editorial signal are included.
02Monthly velocity counts distinct stories, not source articles or headlines.
03Reader activity is aggregated and does not expose individual behavior.