PYSEC-2026-3046 RAGAS has SSRF via Multi-Modal Faithfulness Collections Module

A security flaw has been discovered in vibrantlabsai RAGAS up to 0.4.3. The affected element is the function tryprocesslocalfile/tryprocessurl of the file src/ragas/metrics/collections/multimodalfaithfulness/util.py of the component Collections Module. Performing a manipulation of the argument...

PYSEC-2026-3047 RAGAS has an Arbitrary File Read vulnerability

An Arbitrary File Read vulnerability exists in the ImageTextPromptValue class in Exploding Gradients RAGAS v0.2.3 to v0.2.14. The vulnerability stems from improper validation and sanitization of URLs supplied in the retrievedcontexts parameter when handling multimodal inputs...

Server-side Request Forgery (SSRF)

Overview ragas is an Evaluation framework for RAG and LLM applications Affected versions of this package are vulnerable to Server-side Request Forgery SSRF via improper validation of URLs in the retrievedcontexts parameter when processing multimodal inputs. An attacker can access arbitrary files,...

RAGAS has SSRF via Multi-Modal Faithfulness Collections Module

A security flaw has been discovered in vibrantlabsai RAGAS up to 0.4.3. The affected element is the function tryprocesslocalfile/tryprocessurl of the file src/ragas/metrics/collections/multimodalfaithfulness/util.py of the component Collections Module. Performing a manipulation of the argument...

CVE-2026-6587 vibrantlabsai RAGAS Collections util.py _try_process_url server-side request forgery

A security flaw has been discovered in vibrantlabsai RAGAS up to 0.4.3. The affected element is the function tryprocesslocalfile/tryprocessurl of the file src/ragas/metrics/collections/multimodalfaithfulness/util.py of the component Collections Module. Performing a manipulation of the argument...

CVE-2026-6587 vibrantlabsai RAGAS Collections util.py _try_process_url server-side request forgery

A security flaw has been discovered in vibrantlabsai RAGAS up to 0.4.3. The affected element is the function tryprocesslocalfile/tryprocessurl of the file src/ragas/metrics/collections/multimodalfaithfulness/util.py of the component Collections Module. Performing a manipulation of the argument...

ragas 安全漏洞

Ragas is an open-source toolkit developed by Vibrant Labs for optimizing and evaluating large language models. Versions of Ragas 0.4.3 and earlier contained a security vulnerability. This vulnerability stemmed from improper handling of the parameter retrievedcontexts in the...

CVE-2025-45691

A flaw was found in Ragas. Improper validation of URLs supplied in the retrievedcontexts parameter when handling multimodal inputs leads to Server-Side Request Forgery SSRF. This vulnerability allows attackers to perform arbitrary file reads, conduct internal port scans and access cloud metadata...

EUVD-2025-208315

An Arbitrary File Read vulnerability exists in the ImageTextPromptValue class in Exploding Gradients RAGAS v0.2.3 to v0.2.14. The vulnerability stems from improper validation and sanitization of URLs supplied in the retrievedcontexts parameter when handling multimodal inputs...

CVE-2025-45691

An Arbitrary File Read vulnerability exists in the ImageTextPromptValue class in Exploding Gradients RAGAS v0.2.3 to v0.2.14. The vulnerability stems from improper validation and sanitization of URLs supplied in the retrievedcontexts parameter when handling multimodal inputs...

CVE-2025-45691

An Arbitrary File Read vulnerability exists in the ImageTextPromptValue class in Exploding Gradients RAGAS v0.2.3 to v0.2.14. The vulnerability stems from improper validation and sanitization of URLs supplied in the retrievedcontexts parameter when handling multimodal inputs...

ragas 安全漏洞

Ragas is an open-source toolkit developed by Vibrant Labs for optimizing and evaluating large language models. Versions of Ragas from v0.2.3 to v0.2.14 contain security vulnerabilities. These vulnerabilities stem from improper URL validation and cleaning of the retrievedcontexts parameter, which...

CVE-2025-45691

An Arbitrary File Read vulnerability exists in the ImageTextPromptValue class in Exploding Gradients RAGAS v0.2.3 to v0.2.14. The vulnerability stems from improper validation and sanitization of URLs supplied in the retrievedcontexts parameter when handling multimodal inputs...

Server-side Request Forgery (SSRF)

Overview ragas is an Evaluation framework for RAG and LLM applications Affected versions of this package are vulnerable to Server-side Request Forgery SSRF via improper validation of URLs in the retrievedcontexts parameter when processing multimodal inputs. An attacker can access arbitrary files,...

PT-2026-23468

Name of the Vulnerable Software and Affected Versions Exploding Gradients RAGAS versions 0.2.3 through 0.2.14 Description An arbitrary file read issue exists in the ImageTextPromptValue class. This is due to insufficient validation and sanitization of URLs provided in the retrieved contexts...

CVE-2025-45691

An Arbitrary File Read vulnerability exists in the ImageTextPromptValue class in Exploding Gradients RAGAS v0.2.3 to v0.2.14. The vulnerability stems from improper validation and sanitization of URLs supplied in the retrievedcontexts parameter when handling multimodal inputs...

LLM Embedding-Based Attribution (LEA): Quantifying Source Contributions to Generative Model'S Response for Vulnerability Analysis

Security vulnerabilities are rapidly increasing in frequency and complexity, creating a shifting threat landscape that challenges cybersecurity defenses. Large Language Models LLMs have been widely adopted for cybersecurity threat analysis. When querying LLMs, dealing with new, unseen...

CVE-2023-6969: Authorization Bypass Through User-Controlled Key

The User Shortcodes Plus plugin for WordPress is vulnerable to Insecure Direct Object Reference in all versions up to, and including, 2.0.2 via the usermeta shortcode due to missing validation on a user controlled key. This makes it possible for authenticated attackers, with contributor-level...

CVE-2023-30620 Arbitrary File Write when Extracting a Remotely retrieved Tarball in mindsdb/mindsdb

mindsdb is a Machine Learning platform to help developers build AI solutions. In affected versions an unsafe extraction is being performed using tarfile.extractall from a remotely retrieved tarball. Which may lead to the writing of the extracted files to an unintended location. Sometimes, the...

Insecure Pull Request Submission

Jenkins Pipeline: Shared Groovy is using insecure submission of pull request. It allows attackers able to submit pull requests or equivalent, but not able to commit directly to the configured SCM, to effectively change the Pipeline behavior by changing the definition of a dynamically retrieved...