Vulnerabilities

LlamaIndex (run-llama/llama_index) versions up to and including 0.12.2 contain an uncontrolled resource consumption vulnerability in the VannaPack VannaQueryEngine implementation. The custom_query() logic generates SQL statements from a user-supplied prompt and executes them via vn.run_sql() without enforcing query execution limits In downstream deployments where untrusted users can supply prompts, an attacker can trigger expensive or unbounded SQL operations that exhaust CPU or memory resources, resulting in a denial-of-service condition. The vulnerable execution path occurs in llama_index/packs/vanna/base.py within custom_query().

The llama_index library version 0.12.33 sets the NLTK data directory to a subdirectory of the codebase by default, which is world-writable in multi-user environments. This configuration allows local users to overwrite, delete, or corrupt NLTK data files, leading to potential denial of service, data tampering, or privilege escalation. The vulnerability arises from the use of a shared cache directory instead of a user-specific one, making it susceptible to local data tampering and denial of service.

A vulnerability in the DocugamiReader class of the run-llama/llama_index repository, up to version 0.12.28, involves the use of MD5 hashing to generate IDs for document chunks. This approach leads to hash collisions when structurally distinct chunks contain identical text, resulting in one chunk overwriting another. This can cause loss of semantically or legally important document content, breakage of parent-child chunk hierarchies, and inaccurate or hallucinated responses in AI outputs. The issue is resolved in version 0.3.1.

A vulnerability in the `ObsidianReader` class of the run-llama/llama_index repository, versions 0.12.23 to 0.12.28, allows for arbitrary file read through symbolic links. The `ObsidianReader` fails to resolve symlinks to their real paths and does not validate whether the resolved paths lie within the intended directory. This flaw enables attackers to place symlinks pointing to files outside the vault directory, which are then processed as valid Markdown files, potentially exposing sensitive information.

A critical deserialization vulnerability exists in the run-llama/llama_index library's JsonPickleSerializer component, affecting versions v0.12.27 through v0.12.40. This vulnerability allows remote code execution due to an insecure fallback to Python's pickle module. JsonPickleSerializer prioritizes deserialization using pickle.loads(), which can execute arbitrary code when processing untrusted data. Attackers can exploit this by crafting malicious payloads to achieve full system compromise. The root cause includes an insecure fallback mechanism, lack of validation or safeguards, misleading design, and violation of Python security guidelines.

Multiple vector store integrations in run-llama/llama_index version v0.12.21 have SQL injection vulnerabilities. These vulnerabilities allow an attacker to read and write data using SQL, potentially leading to unauthorized access to data of other users depending on the usage of the llama-index library in a web application.

An SQL injection vulnerability exists in the delete function of DuckDBVectorStore in run-llama/llama_index version v0.12.19. This vulnerability allows an attacker to manipulate the ref_doc_id parameter, enabling them to read and write arbitrary files on the server, potentially leading to remote code execution (RCE).

LLama-Index CLI version v0.12.20 contains an OS command injection vulnerability. The vulnerability arises from the improper handling of the `--files` argument, which is directly passed into `os.system`. An attacker who controls the content of this argument can inject and execute arbitrary shell commands. This vulnerability can be exploited locally if the attacker has control over the CLI arguments, and remotely if a web application calls the LLama-Index CLI with a user-controlled filename. This issue can lead to arbitrary code execution on the affected system.

A Denial of Service (DoS) vulnerability has been identified in the KnowledgeBaseWebReader class of the run-llama/llama_index project, affecting version ~ latest(v0.12.15). The vulnerability arises due to inappropriate secure coding measures, specifically the lack of proper implementation of the max_depth parameter in the get_article_urls 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.

A vulnerability in the FinanceChatLlamaPack of the run-llama/llama_index repository, versions up to v0.12.3, allows for SQL injection in the `run_sql_query` function of the `database_agent`. This vulnerability can be exploited by an attacker to inject arbitrary SQL queries, leading to remote code execution (RCE) through the use of PostgreSQL's large object functionality. The issue is fixed in version 0.3.0.

An issue was discovered in llama_index before 0.10.38. download/integration.py includes an exec call for import {cls_name}.

A command injection vulnerability exists in the RunGptLLM class of the llama_index library, version 0.9.47, used by the RunGpt framework from JinaAI to connect to Language Learning Models (LLMs). The vulnerability arises from the improper use of the eval function, allowing a malicious or compromised LLM hosting provider to execute arbitrary commands on the client's machine. This issue was fixed in version 0.10.13. The exploitation of this vulnerability could lead to a hosting provider gaining full control over client machines.

A command injection vulnerability exists in the run-llama/llama_index repository, specifically within the safe_eval function. Attackers can bypass the intended security mechanism, which checks for the presence of underscores in code generated by LLM, to execute arbitrary code. This is achieved by crafting input that does not contain an underscore but still results in the execution of OS commands. The vulnerability allows for remote code execution (RCE) on the server hosting the application.

LlamaIndex (aka llama_index) through 0.9.34 allows SQL injection via the Text-to-SQL feature in NLSQLTableQueryEngine, SQLTableRetrieverQueryEngine, NLSQLRetriever, RetrieverQueryEngine, and PGVectorSQLQueryEngine. For example, an attacker might be able to delete this year's student records via "Drop the Students table" within English language input.

An issue in llama_index v.0.7.13 and before allows a remote attacker to execute arbitrary code via the `exec` parameter in PandasQueryEngine function.