Making sure the checks get printed
Cisco Talos CAIRN research reveals malware authors embedding natural-language prompt-injection instructions in binaries to evade AI-assisted analysis, succeeding ~35% of the time.
60
- Mentions · 7d0
- Mentions · 30d0
- All mentions4
- First seenSep 22, 2026
- Last mentionedOct 8, 2026
Timeline
4 articles · newest firstAutonomous AI Agents Hack Online Retailers for $25 Per Target, Steal 600,000 Credit Cards
Operator using open-source AI agents Strix, Cairn, and Hermes compromised hundreds of retailers, stealing 600,000+ credit cards at about $25 per target.
78
AI malware just removed the human from the attack loop
Cisco Talos uncovers CLOSEDQUORUM, first 'LLM-as-C2' malware using multi-model judge panel to autonomously steal credentials and crypto wallets.
62
Autonomous AI Agents Hack Retailers for $25 and Steal 600,000 Credit Cards
Gambit Security details an unsupervised AI-agent campaign using Strix, Cairn and Hermes that breached 27+ retailers and stole 600,000+ credit cards for about $25 per target.
78
Related CVEs
by mentions- CVE-2026-8877911%8.7Unauthenticated denial of service in NetScaler ADC and Gateway
Appears with
- Hermesorganization · 2
- Strixorganization · 2
- Magentoorganization · 2
- DeepSeekorganization · 2
- OpenRouterorganization · 2
- Gambit Securityorganization · 2
- Cisco Talosorganization · 2
- Google Geminiorganization · 1
- Warlockthreat actor · 1
- Mistralai model · 1
- Qwenai model · 1
- Anthropicorganization · 1
- MANTLEMAZEorganization · 1
- Kimiai model · 1
- CLOSEDQUORUMorganization · 1
- Citrix NetScalerorganization · 1
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.