Models & APIs · DeepSeek
DeepSeek
DeepSeek models, app and API.
4Advisories
2critical
1high
1medium
2026-10-16Latest
Timeline · advisories per quarter
12024 Q4
22025 Q1
12026 Q4
Named in sources
Reported for DeepSeek
01. CVE-2026-95182: DeepSeek Harness can be tricked into running a planted fake npxDeepSeek Harness (dsh), DeepSeek's developer-preview agent harness, launches MCP servers by bare command name. Injected content can get the model to drop a fake executable into node_modules/.bin, which then runs every time that MCP server starts. DeepSeek 
MCP SDKs & servers 2026-10-16 02. DeepSeek left a database open with chat history and secretsWiz found a publicly accessible DeepSeek database that allowed full control over database operations, exposing over a million lines of logs with chat history and other sensitive data. DeepSeek 2025-01-29 03. OWASP LLM01:2025: prompt injection is the top LLM app riskOWASP ranks prompt injection first in its Top 10 for LLM Applications 2025. Any app that feeds untrusted text to a model with tools or data access is exposed. 
OpenAI 
Anthropic Claude 
Google Gemini +4 more 2024-11-18 04. DeepSeek R1 failed every harmful-prompt test in Cisco’s evaluationCisco ran algorithmic jailbreak testing against DeepSeek and other frontier reasoning models and published the results on 31 January 2025. DeepSeek 2025-01-31
DeepSeek MCP SDKs & servers 2026-10-16 02. DeepSeek left a database open with chat history and secretsWiz found a publicly accessible DeepSeek database that allowed full control over database operations, exposing over a million lines of logs with chat history and other sensitive data. DeepSeek 2025-01-29 03. OWASP LLM01:2025: prompt injection is the top LLM app riskOWASP ranks prompt injection first in its Top 10 for LLM Applications 2025. Any app that feeds untrusted text to a model with tools or data access is exposed. OpenAI Anthropic Claude Google Gemini +4 more 2024-11-18 04. DeepSeek R1 failed every harmful-prompt test in Cisco’s evaluationCisco ran algorithmic jailbreak testing against DeepSeek and other frontier reasoning models and published the results on 31 January 2025. DeepSeek 2025-01-31