gitsafehub
github.com/farhanaliraza/localgpt ↗

farhanaliraza/localgpt

scanned 2026-08-09 · git bec31ed
2 of 6 checks flagged a security issue
🔴 Needs attention
Only 4 of 6 checks finished — treat this as provisional. Re-check ↻

Informational scan, not a security audit. How this is computed.

Leaked secrets✓Vulnerable dependencies33Known OSS vulnerabilities82Risky code patterns✓Malicious dependencies—Project health—

Security checks

Leaked secrets — Gitleaksⓘ none found ✓

API keys, passwords or tokens committed into the repo.

Nothing found by this check. ✓

via Gitleaks v8.21.2 · MIT

Vulnerable dependencies — Trivyⓘ 33 found · 10 serious

Packages you depend on that have known security holes (CVEs).

  • Serious CVE-2023-34540 Langchain OS Command Injection vulnerability
    requirements.txt
    A package you depend on has a known security hole (CVE-2023-34540). Fix: Update that package to its patched version.
  • Serious CVE-2023-34541 Langchain vulnerable to arbitrary code execution
    requirements.txt
    A package you depend on has a known security hole (CVE-2023-34541). Fix: Update that package to its patched version.
  • Serious CVE-2023-36095 langchain Code Injection vulnerability
    requirements.txt
    A package you depend on has a known security hole (CVE-2023-36095). Fix: Update that package to its patched version.
  • Serious CVE-2023-36188 langchain vulnerable to arbitrary code execution
    requirements.txt
    A package you depend on has a known security hole (CVE-2023-36188). Fix: Update that package to its patched version.
  • Serious CVE-2023-36258 langchain arbitrary code execution vulnerability
    requirements.txt
    A package you depend on has a known security hole (CVE-2023-36258). Fix: Update that package to its patched version.
  • Serious CVE-2023-36281 langchain vulnerable to arbitrary code execution
    requirements.txt
    A package you depend on has a known security hole (CVE-2023-36281). Fix: Update that package to its patched version.
  • Serious CVE-2023-38860 LangChain vulnerable to arbitrary code execution
    requirements.txt
    A package you depend on has a known security hole (CVE-2023-38860). Fix: Update that package to its patched version.
  • Serious CVE-2023-38896 LangChain vulnerable to arbitrary code execution
    requirements.txt
    A package you depend on has a known security hole (CVE-2023-38896). Fix: Update that package to its patched version.
  • Serious CVE-2023-39631 Langchain vulnerable to arbitrary code execution via the evaluate function in the numexpr library
    requirements.txt
    A package you depend on has a known security hole (CVE-2023-39631). Fix: Update that package to its patched version.
  • Serious CVE-2023-39659 LangChain vulnerable to arbitrary code execution
    requirements.txt
    A package you depend on has a known security hole (CVE-2023-39659). Fix: Update that package to its patched version.
  • Worth fixing CVE-2023-32786 Langchain Server-Side Request Forgery vulnerability
    requirements.txt
    A package you depend on has a known security hole (CVE-2023-32786). Fix: Update that package to its patched version.
  • Worth fixing CVE-2023-36189 langchain SQL Injection vulnerability
    requirements.txt
    A package you depend on has a known security hole (CVE-2023-36189). Fix: Update that package to its patched version.
  • Worth fixing CVE-2023-46229 langchain: langchain SSRF
    requirements.txt
    A package you depend on has a known security hole (CVE-2023-46229). Fix: Update that package to its patched version.
  • Worth fixing CVE-2026-45134 LangSmith SDK: Public prompt pull deserializes untrusted manifests without trust boundary warning
    requirements.txt
    A package you depend on has a known security hole (CVE-2026-45134). Fix: Update that package to its patched version.
  • Worth fixing CVE-2024-2965 langchain-community: Langchain-community SitemapParser DoS Vulnerability
    requirements.txt
    A package you depend on has a known security hole (CVE-2024-2965). Fix: Update that package to its patched version.
  • Worth fixing CVE-2024-3571 langchain vulnerable to path traversal
    requirements.txt
    A package you depend on has a known security hole (CVE-2024-3571). Fix: Update that package to its patched version.
  • Worth fixing CVE-2026-55443 LangChain: Path traversal and sandbox escape in LangChain file-search middleware and loaders
    requirements.txt
    A package you depend on has a known security hole (CVE-2026-55443). Fix: Update that package to its patched version.
  • Worth fixing CVE-2025-64512 Pdfminer.six is a community maintained fork of the original PDFMiner, ...
    requirements.txt
    A package you depend on has a known security hole (CVE-2025-64512). Fix: Update that package to its patched version.
  • Worth fixing CVE-2025-70559 pdfminer.six before 20251230 contains an insecure deserialization vuln ...
    requirements.txt
    A package you depend on has a known security hole (CVE-2025-70559). Fix: Update that package to its patched version.
  • Worth fixing CVE-2022-1941 protobuf: message parsing vulnerability in ProtocolBuffers
    requirements.txt
    A package you depend on has a known security hole (CVE-2022-1941). Fix: Update that package to its patched version.
  • Worth fixing CVE-2025-4565 python-protobuf: Unbounded recursion in Python Protobuf
    requirements.txt
    A package you depend on has a known security hole (CVE-2025-4565). Fix: Update that package to its patched version.
  • Worth fixing CVE-2026-0994 python: protobuf: Protobuf: Denial of Service due to recursion depth bypass
    requirements.txt
    A package you depend on has a known security hole (CVE-2026-0994). Fix: Update that package to its patched version.
  • Worth fixing CVE-2023-43804 python-urllib3: Cookie request header isn't stripped during cross-origin redirects
    requirements.txt
    A package you depend on has a known security hole (CVE-2023-43804). Fix: Update that package to its patched version.
  • Worth fixing CVE-2025-66418 urllib3: urllib3: Unbounded decompression chain leads to resource exhaustion
    requirements.txt
    A package you depend on has a known security hole (CVE-2025-66418). Fix: Update that package to its patched version.
  • Worth fixing CVE-2025-66471 urllib3: urllib3 Streaming API improperly handles highly compressed data
    requirements.txt
    A package you depend on has a known security hole (CVE-2025-66471). Fix: Update that package to its patched version.
… 8 more not shown

via Trivy v0.70.0 · Apache-2.0

Known OSS vulnerabilities — OSV-Scannerⓘ 82 found · 12 serious

Your dependencies cross-checked against the OSV vulnerability database.

  • Serious PYSEC-2023-109 An issue in langchain v.0.0.64 allows a remote attacker to execute arbitrary code via the PALChain parameter in the Python exec method.
    /workdirs/scan-e5d77045-9ec4-4745-9f99-b2b6460bee4e/requirements.txt
    A package you depend on has a known security hole (CVE-2023-36188). Fix: Update that package to its patched version.
  • Serious PYSEC-2023-138 An issue in Harrison Chase langchain v.0.0.194 allows an attacker to execute arbitrary code via the python exec calls in the PALChain, affected functions include from_math_prompt and from_colored_obje
    /workdirs/scan-e5d77045-9ec4-4745-9f99-b2b6460bee4e/requirements.txt
    A package you depend on has a known security hole (CVE-2023-36095). Fix: Update that package to its patched version.
  • Serious PYSEC-2023-145 An issue in LangChain v.0.0.231 allows a remote attacker to execute arbitrary code via the prompt parameter.
    /workdirs/scan-e5d77045-9ec4-4745-9f99-b2b6460bee4e/requirements.txt
    A package you depend on has a known security hole (CVE-2023-38860). Fix: Update that package to its patched version.
  • Serious PYSEC-2023-146 An issue in Harrison Chase langchain v.0.0.194 and before allows a remote attacker to execute arbitrary code via the from_math_prompt and from_colored_object_prompt functions.
    /workdirs/scan-e5d77045-9ec4-4745-9f99-b2b6460bee4e/requirements.txt
    A package you depend on has a known security hole (CVE-2023-38896). Fix: Update that package to its patched version.
  • Serious PYSEC-2023-147 An issue in langchain langchain-ai v.0.0.232 and before allows a remote attacker to execute arbitrary code via a crafted script to the PythonAstREPLTool._run component.
    /workdirs/scan-e5d77045-9ec4-4745-9f99-b2b6460bee4e/requirements.txt
    A package you depend on has a known security hole (CVE-2023-39659). Fix: Update that package to its patched version.
  • Serious PYSEC-2023-151 An issue in langchain v.0.0.171 allows a remote attacker to execute arbitrary code via the via the a json file to the load_prompt parameter.
    /workdirs/scan-e5d77045-9ec4-4745-9f99-b2b6460bee4e/requirements.txt
    A package you depend on has a known security hole (CVE-2023-36281). Fix: Update that package to its patched version.
  • Serious PYSEC-2023-162 An issue in LanChain-ai Langchain v.0.0.245 allows a remote attacker to execute arbitrary code via the evaluate function in the numexpr library.
    /workdirs/scan-e5d77045-9ec4-4745-9f99-b2b6460bee4e/requirements.txt
    A package you depend on has a known security hole (CVE-2023-39631). Fix: Update that package to its patched version.
  • Serious PYSEC-2023-91 Langchain 0.0.171 is vulnerable to Arbitrary Code Execution.
    /workdirs/scan-e5d77045-9ec4-4745-9f99-b2b6460bee4e/requirements.txt
    A package you depend on has a known security hole (CVE-2023-34540). Fix: Update that package to its patched version.
  • Serious PYSEC-2023-92 Langchain 0.0.171 is vulnerable to Arbitrary code execution in load_prompt.
    /workdirs/scan-e5d77045-9ec4-4745-9f99-b2b6460bee4e/requirements.txt
    A package you depend on has a known security hole (CVE-2023-34541). Fix: Update that package to its patched version.
  • Serious PYSEC-2023-98 An issue in langchain v.0.0.199 allows an attacker to execute arbitrary code via the PALChain in the python exec method.
    /workdirs/scan-e5d77045-9ec4-4745-9f99-b2b6460bee4e/requirements.txt
    A package you depend on has a known security hole (CVE-2023-36258). Fix: Update that package to its patched version.
  • Serious PYSEC-2026-372 Langchain SQL Injection vulnerability
    /workdirs/scan-e5d77045-9ec4-4745-9f99-b2b6460bee4e/requirements.txt
    A package you depend on has a known security hole (CVE-2023-32785). Fix: Update that package to its patched version.
  • Serious PYSEC-2026-2102 AIOHTTP is an asynchronous HTTP client/server framework for asyncio and Python. Prior to version 3.13.4, the C parser (the default for most installs) accepted null bytes and control characters in resp
    /workdirs/scan-e5d77045-9ec4-4745-9f99-b2b6460bee4e/requirements.txt
    A package you depend on has a known security hole (CVE-2026-34520). Fix: Update that package to its patched version.
  • Worth fixing PYSEC-2023-110 SQL injection vulnerability in langchain v.0.0.64 allows a remote attacker to obtain sensitive information via the SQLDatabaseChain component.
    /workdirs/scan-e5d77045-9ec4-4745-9f99-b2b6460bee4e/requirements.txt
    A package you depend on has a known security hole (CVE-2023-36189). Fix: Update that package to its patched version.
  • Worth fixing PYSEC-2023-205 LangChain before 0.0.317 allows SSRF via document_loaders/recursive_url_loader.py because crawling can proceed from an external server to an internal server.
    /workdirs/scan-e5d77045-9ec4-4745-9f99-b2b6460bee4e/requirements.txt
    A package you depend on has a known security hole (CVE-2023-46229). Fix: Update that package to its patched version.
  • Worth fixing PYSEC-2024-118 A Denial-of-Service (DoS) vulnerability exists in the `SitemapLoader` class of the `langchain-ai/langchain` repository, affecting all versions. The `parse_sitemap` method, responsible for parsing site
    /workdirs/scan-e5d77045-9ec4-4745-9f99-b2b6460bee4e/requirements.txt
    A package you depend on has a known security hole (CVE-2024-2965). Fix: Update that package to its patched version.
  • Worth fixing PYSEC-2024-323 A vulnerability in the FAISS.deserialize_from_bytes function of langchain-ai/langchain allows for pickle deserialization of untrusted data. This can lead to the execution of arbitrary commands via the
    /workdirs/scan-e5d77045-9ec4-4745-9f99-b2b6460bee4e/requirements.txt
    A package you depend on has a known security hole (CVE-2024-5998). Fix: Update that package to its patched version.
  • Worth fixing PYSEC-2026-1507 Langchain SQL Injection vulnerability
    /workdirs/scan-e5d77045-9ec4-4745-9f99-b2b6460bee4e/requirements.txt
    A package you depend on has a known security hole (CVE-2024-8309). Fix: Update that package to its patched version.
  • Worth fixing PYSEC-2026-1508 Langchain Server-Side Request Forgery vulnerability
    /workdirs/scan-e5d77045-9ec4-4745-9f99-b2b6460bee4e/requirements.txt
    A package you depend on has a known security hole (CVE-2023-32786). Fix: Update that package to its patched version.
  • Worth fixing PYSEC-2026-1510 langchain vulnerable to path traversal
    /workdirs/scan-e5d77045-9ec4-4745-9f99-b2b6460bee4e/requirements.txt
    A package you depend on has a known security hole (CVE-2024-3571). Fix: Update that package to its patched version.
  • Worth fixing PYSEC-2026-2192 LangChain is a framework for building agents and LLM-powered applications. Prior to 1.3.9, several LangChain components that resolve filesystem paths or expand search patterns do not consistently conf
    /workdirs/scan-e5d77045-9ec4-4745-9f99-b2b6460bee4e/requirements.txt
    A package you depend on has a known security hole (CVE-2026-55443). Fix: Update that package to its patched version.
  • Worth fixing PYSEC-2026-2555 LangSmith SDK: Public prompt pull deserializes untrusted manifests without trust boundary warning
    /workdirs/scan-e5d77045-9ec4-4745-9f99-b2b6460bee4e/requirements.txt
    A package you depend on has a known security hole (CVE-2026-45134). Fix: Update that package to its patched version.
  • Worth fixing PYSEC-2026-1805 protobuf affected by a JSON recursion depth bypass
    /workdirs/scan-e5d77045-9ec4-4745-9f99-b2b6460bee4e/requirements.txt
    A package you depend on has a known security hole (CVE-2026-0994). Fix: Update that package to its patched version.
  • Worth fixing PYSEC-2026-1806 protobuf-python has a potential Denial of Service issue
    /workdirs/scan-e5d77045-9ec4-4745-9f99-b2b6460bee4e/requirements.txt
    A package you depend on has a known security hole (CVE-2025-4565). Fix: Update that package to its patched version.
  • Worth fixing PYSEC-2026-899 protobuf-cpp and protobuf-python have potential Denial of Service issue
    /workdirs/scan-e5d77045-9ec4-4745-9f99-b2b6460bee4e/requirements.txt
    A package you depend on has a known security hole (CVE-2022-1941). Fix: Update that package to its patched version.
  • Worth fixing PYSEC-2023-192 urllib3 is a user-friendly HTTP client library for Python. urllib3 doesn't treat the `Cookie` HTTP header special or provide any helpers for managing cookies over HTTP, that is the responsibility of t
    /workdirs/scan-e5d77045-9ec4-4745-9f99-b2b6460bee4e/requirements.txt
    A package you depend on has a known security hole (CVE-2023-43804). Fix: Update that package to its patched version.
… 57 more not shown

via OSV-Scanner v1.9.2 · Apache-2.0

Risky code patterns — Semgrepⓘ none found ✓

Code that can be exploited: injection, hardcoded credentials and similar.

Nothing found by this check. ✓

via Semgrep v1.147.0 · LGPL-2.1

Malicious dependencies — Guarddogⓘ timed out

Packages that look intentionally malicious: typosquats, sneaky install scripts.

This check didn’t finish — that’s not the same as “clean.” Try Check again above.

via Guarddog v2.10.0 · Apache-2.0

error: pypi:timeout

Project health

A signal about how the project is maintained — not a vulnerability in your code. It doesn’t affect the verdict above.

Project health — OpenSSF Scorecardⓘ didn’t run

Maintenance & supply-chain hygiene. A signal about the project, not a vulnerability in your code.

This check didn’t finish — that’s not the same as “clean.” Try Check again above.

via OpenSSF Scorecard · Apache-2.0

About these results. Six open-source checks ran in parallel; every finding is tagged with the tool that produced it. The verdict follows a published rule. False positives and false negatives are normal — a clean scan does not mean the code is secure, and a red verdict does not mean the project is compromised.