Searching for Privacy Risks in LLM Agents Via Simulation

The widespread deployment of LLM-based agents is likely to introduce a critical privacy threat: malicious agents that proactively engage others in multi-turn interactions to extract sensitive information. These dynamic dialogues enable adaptive attack strategies that can cause severe privacy...

fair-llm (>=0.2.0, <=0.6.2), geo-importer (>=0.0.1b1, <=0.0.1b914) +4 more potentially affected by CVE-2025-55197 via pypdf (5.6.0)

pypdf PYPI version 5.6.0 is affected by a known vulnerability. The following packages have a transitive dependency on pypdf and may be impacted: - fair-llm =0.2.0, =0.0.1b1, =30.0.5, =30.0.7 - textspitter 0.4.0b0 Source cves: CVE-2025-55197 Source advisory: OSV:GHSA-7HFW-26VP-JP8M...

ai.ancf.lmos-router:lmos-router-llm-in-spring-cloud-gateway-demo (>=0.2.0, <=0.28.0), ai.ancf.lmos:lmos-operator (>=0.0.4, <=0.6.0) +7685 more potentially affected by CVE-2025-48989 via org.apache.tomcat.embed:tomcat-embed-core (>=10.1.0-m1, <=10.1.43)

org.apache.tomcat.embed:tomcat-embed-core MAVEN version =10.1.0-m1, =0.2.0, =0.0.4, =0.5.0, =0.6.0, =0.5.0, =0.7.0, =0.7.0, =0.5.0, =0.7.5, =0.8.3, =0.7.0, =0.5.0, =0.5.0, =0.5.0, =0.9.2 and more Source cves: CVE-2025-48989 Source advisory: OSV:GHSA-GQP3-2CVR-X8M3...

ai.ancf.lmos-router:lmos-router-llm-in-spring-cloud-gateway-demo (>=0.2.0, <=0.28.0), ai.ancf.lmos:lmos-router-llm-in-spring-cloud-gateway-demo (0.1.0) +13338 more potentially affected by CVE-2025-8916 via org.bouncycastle:bcprov-jdk18on (>=1.71, <=1.78.1)

org.bouncycastle:bcprov-jdk18on MAVEN version =1.71, =0.2.0, =0.31.0, =0.5.0, =0.6.0, =0.5.0, =0.6.0, =0.5.0, =0.9.1, =0.7.0, =0.7.0, =0.5.0, =0.8.3, =0.8.3, =0.8.3, =0.9.0 and more Source cves: CVE-2025-8916 Source advisory: SNYK:JAVA-ORGBOUNCYCASTLE-11789695...

ai.ancf.lmos-router:lmos-router-llm-in-spring-cloud-gateway-demo (>=0.2.0, <=0.28.0), ai.ancf.lmos:lmos-router-llm-in-spring-cloud-gateway-demo (0.1.0) +13338 more potentially affected by CVE-2025-8916 via org.bouncycastle:bcprov-jdk18on (>=1.71, <=1.78.1)

org.bouncycastle:bcprov-jdk18on MAVEN version =1.71, =0.2.0, =0.31.0, =0.5.0, =0.6.0, =0.5.0, =0.6.0, =0.5.0, =0.9.1, =0.7.0, =0.7.0, =0.5.0, =0.8.3, =0.8.3, =0.8.3, =0.9.0 and more Source cves: CVE-2025-8916 Source advisory: MEND:CVE-2025-8916...

CVE-2025-45146

ModelCache for LLM through v0.2.0 was discovered to contain an deserialization vulnerability via the component /manager/datamanager.py. This vulnerability allows attackers to execute arbitrary code via supplying crafted data...

CVE-2025-45146: Deserialization of Untrusted Data

ModelCache for LLM through v0.2.0 was discovered to contain an deserialization vulnerability via the component /manager/datamanager.py. This vulnerability allows attackers to execute arbitrary code via supplying crafted data...

BentoML Detected

This is an informational plugin to inform the user that the scanner has detected a publicly accessible BentoML instance on the target application. BentoML is an open-source inference platform. This detection is included in the AI and LLM category. No source data...

CVE-2025-51864

A reflected cross-site scripting XSS vulnerability exists in AIBOX LLM chat chat.aibox365.cn through 2025-05-27, allowing attackers to hijack accounts through stolen JWT tokens...

CVE-2025-51864

A reflected cross-site scripting XSS vulnerability exists in AIBOX LLM chat chat.aibox365.cn through 2025-05-27, allowing attackers to hijack accounts through stolen JWT tokens...

CVE-2025-51864

A reflected cross-site scripting (XSS) vulnerability exists in the AIBOX LLM chat component (chat.aibox365.cn) for versions through 2025-05-27 . The flaw allows attackers to bypass fragile backend filters—potentially by using specific malicious prompts or inserting characters before and after pay...

CVE-2025-51864

A reflected cross-site scripting XSS vulnerability exists in AIBOX LLM chat chat.aibox365.cn through 2025-05-27, allowing attackers to hijack accounts through stolen JWT tokens...

CVE-2025-51864

A reflected cross-site scripting XSS vulnerability exists in AIBOX LLM chat chat.aibox365.cn through 2025-05-27, allowing attackers to hijack accounts through stolen JWT tokens...

PT-2025-30422 · Aibox Llm · Aibox Llm

Name of the Vulnerable Software and Affected Versions: AIBOX LLM chat versions through 2025-05-27 Description: A reflected cross-site scripting XSS issue exists, potentially allowing attackers to hijack accounts through stolen JWT tokens. Recommendations: At the moment, there is no information...

Deepfiction AI security vulnerabilities

Deepfiction AI is an artificial intelligence platform from Deepfiction AI. A security vulnerability exists in Deepfiction AI versions 2025-06-03 and earlier that stems from an unsafe direct object reference that could lead to the use of other user credits to chat with LLM...

CVE-2025-51864: Improper Neutralization of Input During Web Page Generation

A reflected cross-site scripting XSS vulnerability exists in AIBOX LLM chat chat.aibox365.cn through 2025-05-27, allowing attackers to hijack accounts through stolen JWT tokens...

AI and LLM Bot Management Has Become a Business-Critical Issue: Do It Right

AI bots, agents, and LLM scrapers all want your content. Here’s how to manage them so that they help, not hinder, your business...

CVE-2025-53630

llama.cpp is an inference of several LLM models in C/C++. Integer Overflow in the ggufinitfromfileimpl function in ggml/src/gguf.cpp can lead to Heap Out-of-Bounds Read/Write. This vulnerability is fixed in commit 26a48ad699d50b6268900062661bd22f3e792579...

CAVGAN: Unifying Jailbreak and Defense of LLMs Via Generative Adversarial Attacks on Their Internal Representations

Security alignment enables the Large Language Model LLM to gain the protection against malicious queries, but various jailbreak attack methods reveal the vulnerability of this security mechanism. Previous studies have isolated LLM jailbreak attacks and defenses. We analyze the security protection...

berri-ai (>=0.18.2, <=0.21.3), browserpilot (>=0.1.1, <=0.2.34) +6 more potentially affected by CVE-2025-6210 via llama-index (>=0.4.17, <=0.4.40)

llama-index PYPI version =0.4.17, =0.18.2, =0.1.1, =0.1.0, =0.0.1, =10.9.6, =0.7.0, =0.0.36, =0.0.37 Source cves: CVE-2025-6210 Source advisory: OSV:PYSEC-2025-252...