CVE-2026-50181

CVE-2026-50181 Langroid 파일 도구의 경로 탐색으로 인해 설정된 현재 디렉토리 외부에서 읽기/쓰기가 허용되었습니다. 기본 권고: GHSA-fg23-3346-88f5 GitHub 권고 데이터베이스: github.com/advisories/GHSA-fg23-3346-88f5 연구자 크레딧: @chaitanyagarware 한눈에 보기 필드| 값 ---|--- CVE| CVE-2026-50181 GHSA| GHSA-fg23-3346-88f5 프로젝트| langroid/langroid 패키지| langroid 생태계...

PYSEC-2026-2577 Langroid: SQLChatAgent dangerous-function blocklist can be bypassed with quoted or schema-qualified pg_read_file calls

SQLChatAgent validatequery dangerous-pattern regex is bypassable via quoted/commented/qualified function names Summary The SQLChatAgent SQL-injection mitigation, with default allowdangerousoperations=False, combines a raw-text regex blocklist DANGEROUSSQLPATTERNS with a sqlglot SELECT-only...

PYSEC-2026-2579 Langroid: handle_message() executes user-supplied tool JSON without sender verification

Summary A Langroid application exposing a chat interface to untrusted users may allow direct tool invocation via raw JSON payloads, even when tools are registered with use=False, handle=True. Details enablemessage..., use=False, handle=True only prevents the LLM from being instructed to generate...

Langroid: handle_message() executes user-supplied tool JSON without sender verification

SummaryA Langroid application exposing a chat interface to untrusted users may allow direct tool invocation via raw JSON payloads, even when tools are registered with use=False, handle=True. Detailsenablemessage..., use=False, handle=True only prevents the LLM from being instructed to generate th...

Langroid: Neo4jChatAgent executes LLM-generated Cypher without validation (prompt-to-Cypher injection; config-conditional RCE), mirroring the SQLChatAgent bug fixed in CVE-2026-25879

Neo4jChatAgent passes LLM-generated Cypher queries straight to the Neo4j driver with no validation, no statement-type allowlist, and no opt-out gate. The query text is influenceable by prompt injection direct user input or indirect content the agent reads back via RAG, so an attacker who can...

PYSEC-2026-2578 Langroid: Path traversal in the file tools allows read/write outside configured current directory

Summary Langroid's ReadFileTool and WriteFileTool appear to treat currdir as the intended working-directory boundary for file operations. However, the tools only change the process working directory to currdir and then operate on the user-supplied filepath without resolving and enforcing that the...

PYSEC-2026-2580 Langroid: SQLChatAgent _validate_query blocklist misses pg_read_file family enabling arbitrary file read

Summary SQLChatAgent in langroid ships a validatequery defense-in-depth layer whose DANGEROUSSQLPATTERNS regex blocklist enumerates dangerous SQL primitives by specific function name. The list misses the canonical PostgreSQL filesystem-disclosure family pgreadfile, pgstatfile, pglslogdir,...

PT-2026-59233

Summary Langroid's ReadFileTool and WriteFileTool appear to treat curr dir as the intended working-directory boundary for file operations. However, the tools only change the process working directory to curr dir and then operate on the user-supplied file path without resolving and enforcing that...

PT-2026-59234

Summary A Langroid application exposing a chat interface to untrusted users may allow direct tool invocation via raw JSON payloads, even when tools are registered with use=False, handle=True. Details enable message..., use=False, handle=True only prevents the LLM from being instructed to generate...

CVE-2026-55615

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.65.5, Neo4jChatAgent passes LLM-generated Cypher queries straight to the Neo4j driver with no validation, no statement-type allowlist, and no opt-out gate. The query text is influenceable by prompt...

CVE-2026-54760

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.65.1, the SQLChatAgent SQL-injection mitigation, with default allowdangerousoperations=False, combines a raw-text regex blocklist DANGEROUSSQLPATTERNS with a sqlglot SELECT-only statement allowlist...

CVE-2026-54771

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.65.3, a Langroid application exposing a chat interface to untrusted users may allow direct tool invocation via raw JSON payloads, even when tools are registered with use=False, handle=True. Version...

CVE-2026-50180

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.64.0, SQLChatAgent in langroid ships a validatequery defense-in-depth layer whose DANGEROUSSQLPATTERNS regex blocklist enumerates dangerous SQL primitives by specific function name. The list misses...

CVE-2026-54769

Langroid is a framework for building large-language-model-powered applications. Versions prior to 0.65.2 are vulnerable to a critical Sandbox Escape leading to Remote Code Execution RCE in its TableChatAgent and VectorStore capabilities. When these agents evaluate LLM-generated tool messages with...

CVE-2026-50180: Improper Limitation of a Pathname to a Restricted Directory

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.64.0, SQLChatAgent in langroid ships a validatequery defense-in-depth layer whose DANGEROUSSQLPATTERNS regex blocklist enumerates dangerous SQL primitives by specific function name. The list misses...

CVE-2026-50181: Improper Limitation of a Pathname to a Restricted Directory

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.64.0, Langroid's ReadFileTool and WriteFileTool appear to treat currdir as the intended working-directory boundary for file operations. However, the tools only change the process working directory t...

CVE-2026-55615: Improper Neutralization of Special Elements in Output Used by a Downstream Component

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.65.5, Neo4jChatAgent passes LLM-generated Cypher queries straight to the Neo4j driver with no validation, no statement-type allowlist, and no opt-out gate. The query text is influenceable by prompt...

CVE-2026-54760: Improper Limitation of a Pathname to a Restricted Directory

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.65.1, the SQLChatAgent SQL-injection mitigation, with default allowdangerousoperations=False, combines a raw-text regex blocklist DANGEROUSSQLPATTERNS with a sqlglot SELECT-only statement allowlist...

CVE-2026-54769: Improper Control of Generation of Code

Langroid is a framework for building large-language-model-powered applications. Versions prior to 0.65.2 are vulnerable to a critical Sandbox Escape leading to Remote Code Execution RCE in its TableChatAgent and VectorStore capabilities. When these agents evaluate LLM-generated tool messages with...

CVE-2026-54771: Failure to Sanitize Special Elements into a Different Plane (Special Element Injection)

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.65.3, a Langroid application exposing a chat interface to untrusted users may allow direct tool invocation via raw JSON payloads, even when tools are registered with use=False, handle=True. Version...