https://cve.radiocsirt.org Contains only the most 10 recent entries. http://www.rssboard.org/rss-specification python-feedgen en Fri, 02 Oct 2026 23:23:44 +0000 https://cve.radiocsirt.org/vuln/cve-2026-34070 <p><strong>Affected:</strong> langchain-ai langchain, Red Hat Ansible Automation Platform 2.5, Red Hat OpenShift AI 3.3, Red Hat OpenShift Lightspeed, Red Hat Ansible Automation Platform 2, Red Hat OpenShift AI (RHOAI)</p> <p>LangChain is a framework for building agents and LLM-powered applications. Prior to version 1.2.22, multiple functions in langchain_core.prompts.loading read files from paths embedded in deserialized config dicts without validating against directory traversal or absolute path injection. When an application passes user-influenced prompt configurations to load_prompt() or load_prompt_from_config(), an attacker can read arbitrary files on the host filesystem, constrained only by file-extension checks (.txt for templates, .json/.yaml for examples). This issue has been patched in version 1.2.22.</p> <p><strong>Affected:</strong> langchain-ai langchain, Red Hat Ansible Automation Platform 2.5, Red Hat OpenShift AI 3.3, Red Hat OpenShift Lightspeed, Red Hat Ansible Automation Platform 2, Red Hat OpenShift AI (RHOAI)</p> <p>LangChain is a framework for building agents and LLM-powered applications. Prior to version 1.2.22, multiple functions in langchain_core.prompts.loading read files from paths embedded in deserialized config dicts without validating against directory traversal or absolute path injection. When an application passes user-influenced prompt configurations to load_prompt() or load_prompt_from_config(), an attacker can read arbitrary files on the host filesystem, constrained only by file-extension checks (.txt for templates, .json/.yaml for examples). This issue has been patched in version 1.2.22.</p> https://cve.radiocsirt.org/vuln/cve-2026-34070 https://cve.radiocsirt.org/vuln/ghsa-qh6h-p6c9-ff54 <p><strong>Affected:</strong> PyPI: langchain-core</p> <p>## Summary</p> <p>Multiple functions in `langchain_core.prompts.loading` read files from paths embedded in deserialized config dicts without validating against directory traversal or absolute path injection. When an application passes user-influenced prompt configurations to `load_prompt()` or `load_prompt_from_config()`, an attacker can read arbitrary files on the host filesystem, constrained only by file-extension checks (`.txt` for templates, `.json`/`.yaml` for examples).</p> <p>**Note:** The affected functions (`load_prompt`, `load_prompt_from_config`, and the `.save()` method on prompt classes) are undocumented legacy APIs. They are superseded by the `dumpd`/`dumps`/`load`/`loads` serialization APIs in `langchain_core.load`, which do not perform filesystem reads and use an allowlist-based security model. As part of this fix, the legacy APIs have been formally deprecated and will be removed in 2.0.0.</p> <p>## Affected component</p> <p>**Package:** `langchain-core` **File:** `langchain_core/prompts/loading.py` **Affected functions:** `_load_template()`, `_load_examples()`, `_load_few_shot_prompt()`</p> <p>## Severity</p> <p>**High**</p> <p>The score reflects the file-extension constraints that limit which files can be read.</p> <p>## Vulnerable code paths</p> <p>| Config key | Loaded by | Readable extensions | |---|---|---| | `template_path`, `suffix_path`, `prefix_path` | `_load_template()` | `.txt` | | `examples` (when string) | `_load_examples()` | `.json`, `.yaml`, `.yml` | | `example_prompt_path` | `_load_few_shot_pr…</p> <p><strong>Affected:</strong> PyPI: langchain-core</p> <p>## Summary</p> <p>Multiple functions in `langchain_core.prompts.loading` read files from paths embedded in deserialized config dicts without validating against directory traversal or absolute path injection. When an application passes user-influenced prompt configurations to `load_prompt()` or `load_prompt_from_config()`, an attacker can read arbitrary files on the host filesystem, constrained only by file-extension checks (`.txt` for templates, `.json`/`.yaml` for examples).</p> <p>**Note:** The affected functions (`load_prompt`, `load_prompt_from_config`, and the `.save()` method on prompt classes) are undocumented legacy APIs. They are superseded by the `dumpd`/`dumps`/`load`/`loads` serialization APIs in `langchain_core.load`, which do not perform filesystem reads and use an allowlist-based security model. As part of this fix, the legacy APIs have been formally deprecated and will be removed in 2.0.0.</p> <p>## Affected component</p> <p>**Package:** `langchain-core` **File:** `langchain_core/prompts/loading.py` **Affected functions:** `_load_template()`, `_load_examples()`, `_load_few_shot_prompt()`</p> <p>## Severity</p> <p>**High**</p> <p>The score reflects the file-extension constraints that limit which files can be read.</p> <p>## Vulnerable code paths</p> <p>| Config key | Loaded by | Readable extensions | |---|---|---| | `template_path`, `suffix_path`, `prefix_path` | `_load_template()` | `.txt` | | `examples` (when string) | `_load_examples()` | `.json`, `.yaml`, `.yml` | | `example_prompt_path` | `_load_few_shot_pr…</p> https://cve.radiocsirt.org/vuln/ghsa-qh6h-p6c9-ff54