Skip to content

Topic

Red-Teaming

Adversarial security practice where testers simulate real attackers against an organisation's own systems to uncover exploitable weaknesses.

Current stories

buildOne report1 publisher

Edited transcripts slipped 35 attacks past Redwood's action-only monitors in 252 runs

Redwood's Screwtape pipeline produced 35 monitor-evading attacks from 252 runs on 94 unique Redwood staff transcripts. Six of them also got past a frontier developer's monitor and were confirmed valid by human review.

Publishers:lesswrong.com

Reality

Evidence55
Adoption
Not scored
Hype gap−10
Incentives
Not scored
Confidence50
buildOne report1 publisher

X-AgentRed searches a tool-dependency graph for harm that only appears when agents chain calls

X-AgentRed builds a directed graph of tool dependencies to find harmful call chains across Gmail, Slack, Jira and payment APIs. It targets the gap left by single-tool security testing, where each call looks reasonable alone and the harm exists only in the sequence.

Publishers:dev.to

Reality

Evidence30
Adoption
Not scored
Hype gap
Not scored
Incentives
Not scored
Confidence40
leadershipOne report1 publisher

Triage and tuning decided which SOC caught CISA's red team

CISA's red team breached two critical-sector organisations, and only the water-sector one contained it, isolating machines in up to 20 minutes. The gap traces to alert tuning and triage, so the first fix most SOCs need is analyst time.

Publishers:itpro.com

Reality

Evidence45
Adoption
Not scored
Hype gap+20
Incentives55
Confidence45
productOne report1 publisher

RemoteThreat pitches enterprise red teams a platform so they stop building their own tools

RemoteThreat launched with $7 million to sell enterprise red teams and U.S. government mission teams one platform for running offensive cyber operations. It is pitched as a way for expert operators to skip building their own tool chains.

Publishers:siliconangle.com

Reality

Evidence30
Adoption15
Hype gap+35
Incentives70
Confidence30
securityConfirmed5 publishers

CISA ran the same tradecraft at two organisations; only the water utility caught it

Detection at the first hop forced CISA's red team onto donated access at Organization B. It did not stop the team reaching the same sensitive systems it reached at Organization A.

Perspective Coverage

5 publishers
Builder
Builder 39%
Operator
Operator 53%
Investor
Investor 8%

Reality

Evidence76
Adoption
Not scored
Hype gap+12
Incentives35
Confidence72
securityOne report1 publisher

Researchers confirmed 157 malicious skills in a sweep of 98,380 across two agent marketplaces

A securityaffairs.com analysis maps a single month of AI security papers onto MITRE ATLAS. The techniques land on agent skills, the Model Context Protocol and injection strings found by reinforcement learning.

Reality

Evidence38
Adoption45
Hype gap+25
Incentives55
Confidence45
investConfirmed3 publishers

Anthropic buys its own safety audit while calling for pooled or government funding

Accenture's Faculty unit will embed staff inside Anthropic to red-team models and test safeguards, Anthropic is paying for the work itself, and both sides have put at least $1 billion behind it over five years.

Perspective Coverage

3 publishers
Builder
Builder 30%
Operator
Operator 38%
Investor
Investor 32%

Reality

Evidence55
Adoption20
Hype gap+35
Incentives80
Confidence62
securityOne report1 publisher

Refusal-stripped open-source agents broke five of a researcher's own accounts in five hours

Shrivu Shankar rented cloud GPUs, pointed about 100 abliterated open-source agents at his own name, and five hours later two weak passwords and three old side projects had fallen while his Gmail, 1Password and bank held.

Publishers:blog.sshh.io

Reality

Evidence44
Adoption22
Hype gap+9
Incentives36
Confidence55
productOne report1 publisher

Amazon puts Mandiant's founder on both its Audit and Security committees

Kevin Mandia joined Amazon's board on 8 September and takes two committee seats, including the security one a retired NSA director left in May. His day job is an AI startup that attacks corporate networks.

Publishers:thenextweb.com

Reality

Evidence74
Adoption30
Hype gap+30
Incentives76
Confidence64
securityOne report1 publisher

Abliteration.ai puts guardrail-stripped open-weight models behind a browser and an API

Open weights could always be modified. Hosting them for anyone who signs up is the new part. That lands the uncensored-model question on whoever approves red-team tooling. Whether that helps defenders is contested.

Publishers:scworld.com

Reality

Evidence24
Adoption8
Hype gap+32
Incentives68
Confidence34