Product
Dify
- First Reported
- Jun 22, 2026
- Latest Reported
- Nov 16, 2026
Reported Context (8)
- Attackers' AI agents have been hunting for weak spots in internet-exposed AI apps such as LiteLLM, One API, and Dify to steal the AI provider keys stored inside, according to the agents' own records. Amazon Tracks AI-Agent Campaign Targeting Exposed AI Apps for API Keys
- Targets included LLM gateways and proxy platforms such as One API, New API, Veloera, Sub2API, and LiteLLM, and AI application builders such as Dify, FastGPT, Langflow, RAGFlow, Open WebUI, LobeChat, and Ollama. Amazon Details ARTEX AI-Agent Campaigns Targeting AI Credentials and Crypto KYC
- As the enterprise adoption of agentic AI accelerates, particularly through workflow platforms such as Dify and n8n, new vulnerabilities will emerge. Trend Micro Predicts AI-Driven Attacks and Agent Security Risks Will Grow in 2026
- 81.70.240.170The exposed configurations disclosed multiple downstream AI-platform credentials, including Dify application keys, a Coze private key and platform AI credential material. The Dify credentials were then Chinese-Speaking Operator Used AI Agents to Target Government and Education Systems Across Asia
- CVE-2026-41948: a path traversal vulnerability in the Dify AI platform Kaspersky Reports Rising Vulnerability Disclosures and Early Exploit Releases in Q2 2026
CVE (41)
Malware (6)
People (4)
Threat Actors (9)
MITRE ATT&CK (24)
Vendors (11)
Products (60)
Tools (14)
Industries (18)
Countries (12)
Note: Related entities, including threat actors, malware, CVEs, MITRE ATT&CK techniques, vendors, products, tools, countries, and industries, are shown when they appear in the same reporting. Their presence does not necessarily mean they were targeted, compromised, vulnerable, responsible for the activity, or directly involved in the incident.
