CarryoverBench: planted LLM-agent injections re-fire after the attacker leaves
On five frontier models, planted payloads showed no measurable decay over five rounds once planting succeeded.
58
Product
Hermes
- Mentions · 7d0
- Mentions · 30d5
- All mentions15
- First seenAug 12, 2026
- Last mentioned10d ago
Timeline
15 articles · newest firstReconstructing AI Agent Activity: Two New Scripts for Forensic Review, (Thu, Oct 8th)
SANS published two Python scripts that reconstruct OpenCode and Hermes AI agent activity for forensic review.
44
Nous Research confirms it hit $1.5B valuation, launches AI agents for business users
Nous Research raised $90 million at a $1.5 billion valuation and launched Hermes for Businesses.
54
Harness Engineering for Software Engineering via Modular Executable Dev-Primitives
HERMES uses modular Dev-Primitives to beat baseline software-engineering agent harnesses by 12.4% on four benchmarks.
54
All the AI agents that can live in your text messages
TechCrunch surveys text-message AI agents, including Instinct, valued at $10 billion after a $1 billion round.
36
AI tools help hacker break in for $25 per target
AI-driven campaign compromised 27 of 105 retailers and stole about 600,000 card numbers.
74
Crook used three open source agents to break into a Fortune 500 hospitality company, a major US airline and 25+ other orgs
An operator used three open-source AI agents to compromise at least 27 organizations and steal over 600,000 card records.
86
AI-Powered Campaign Targets Hundreds of Online Retailers
A Chinese-speaking actor used autonomous AI agents to compromise online retailers and steal over 600,000 credit cards.
86
Malicious AI agents steal 600K credit cards, infect 100+ sites with skimmers
An AI-agent campaign stole over 600,000 cards and skimmer-infected at least 119 retail sites.
85
This Digital Radio Gets Messages to the World’s Remotest Locations
Rhizomatica's open-source HERMES shortwave system sends files and SOS messages for remote communities.
4
BlackHatSect0r Hackers Disable AI Safety Controls to Automate Credential Theft and Cyberattacks
French-speaking crew BlackHatSect0r disabled AI agent safety controls to automate scanning, credential harvesting, and vishing, exposing 16,834 stolen credentials.
62
AI Coding Agents Are Installing Unknown/Untrusted Code on Corporate Networks
Researchers found 120 corporate llms.txt files pointing to unregistered packages, demonstrating AI coding agents install and execute attacker-controlled code on Fortune 500 networks.
65
Claude, Codex, and Hermes installed unowned code inside corporate networks
Analysis found 227 install commands from Claude, Codex, and Hermes agents inside corporate networks pointing to packages with no verifiable owner.
60
China-Linked Hackers Use AI Agents in Autonomous Attack on Taiwan
Suspected Chinese hackers used eight AI agents to autonomously breach Taiwan government networks, compromising 85+ accounts and stealing 2,500 personnel records.
86
Researchers observe first ‘near-autonomous’ AI attack on government target in Taiwan
Dream researchers observed the first near-autonomous AI attack on a government target, with suspected Chinese hackers stealing 2,500+ Taiwan records.
82
Related CVEs
by mentions- CVE-2026-425306%9.2NGINX Open Source has a vulnerability in the ngx_http_v3_module module
Appears with
- Anthropicorganization · 5
- Strixproduct · 4
- OpenRouterorganization · 4
- Gambitorganization · 4
- Cairnproduct · 4
- Hermesai model · 3
- Codexproduct · 3
- Anthropicvendor · 3
- Dream Securityvendor · 2
- Taiwan governmentvictim · 2
- DeepSeekvendor · 2
- Claudeproduct · 2
- Nous Researchorganization · 2
- Claude Opus 4.6ai model · 2
- Magentoproduct · 2
- Financial Timesorganization · 2
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.