LlamaIndex Vulnerable to Denial of Service (DoS)
CVE-2025-1752 · GHSA-7c85-87cp-mr6g · published 2025-05-10 · updated 2025-10-15
- Severity
- High
- CVSS score
- 7.5
- Chance of exploitation (EPSS)
- 0.53%
- Fixed in
- 0.12.21
- Exploitation Public proof of concept
- Automatable Yes
- Technical impact Partial
- CISA SSVC
A Denial of Service (DoS) vulnerability has been identified in the KnowledgeBaseWebReader class of the run-llama/llamaindex project, affecting version ~ latest(v0.12.15). The vulnerability arises due to inappropriate secure coding measures, specifically the lack of proper implementation of the maxdepth parameter in the getarticleurls function. This allows an attacker to exhaust Python's recursion limit through repeated function calls, leading to resource consumption and ultimately crashing the Python process.
Upgrade llama-index to 0.12.21 or later. If you start it from an MCP config with npx or uvx, pin that version so an old cached copy is not used.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| llama-index | PyPI | >= 0.12.15, < 0.12.21 | 0.12.21 |
- HightsParticles: Unbounded HTTP Request Body Buffering in @tsparticles/mcp-server Leads to Remote DoS@tsparticles/mcp-server
- HighMissing request-wide media budget allows single-request frontend resource exhaustionvllm
- HighMCP TypeScript SDK: HTTP server transports and handlers did not limit request body size or JSON-RPC batch length@modelcontextprotocol/hono, @modelcontextprotocol/node, @modelcontextprotocol/sdk, @modelcontextprotocol/server
- HighvLLM : DoS via unvalidated mm_processor_kwargs in multimodal image processors (Isaac, InternVL, H2OVL, etc.)vllm
- HighMCP TypeScript SDK: One HTTP request within the default size limit could exhaust server memory during validation@modelcontextprotocol/sdk, @modelcontextprotocol/server
- HighFrame-count cap bypass in VideoMediaIO.load_base64 for video/jpeg via media_io_kwargs.video.num_framesvllm
- Criticalllama_index vulnerable to SQL Injectionllama-index
- CriticalSQL injection in llama-indexllama-index
- Criticalllama-index vulnerable to arbitrary code executionllama-index
- Highllama-index has Insecure Temporary Filellama-index
- HighLlamaIndex vulnerable to Creation of Temporary File in Directory with Insecure Permissionsllama-index
- HighRunGptLLM class in LlamaIndex has a command injectionllama-index
The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.