CVE-2026-116691

A flaw was found in MLflow. This vulnerability can lead to sensitive information disclosure when using the CrewAI autologging integration, which serializes agent objects into trace telemetry without sanitizing credential fields. Consequently, plaintext application programming interface API keys f...

CVE-2026-120630

CrewAI contains an SSRF vulnerability caused by its SSRF guard and HTTP client, which both miss malicious content in URLs by checking opposite content passed to it, enabling any request that injects a malicious URL to perform SSRF, such as with the ScrapWebsiteTool...

CVE-2026-120630 CVE-2026-120630

CrewAI contains an SSRF vulnerability caused by its SSRF guard and HTTP client, which both miss malicious content in URLs by checking opposite content passed to it, enabling any request that injects a malicious URL to perform SSRF, such as with the ScrapWebsiteTool...

CVE-2026-120630 CVE-2026-120630

CrewAI contains an SSRF vulnerability caused by its SSRF guard and HTTP client, which both miss malicious content in URLs by checking opposite content passed to it, enabling any request that injects a malicious URL to perform SSRF, such as with the ScrapWebsiteTool...

CVE-2026-120630

The CrewAI framework contains a Server-Side Request Forgery (SSRF) vulnerability. The root cause is a logic flaw where the SSRF guard and the HTTP client fail to detect malicious content in URLs because they validate different aspects of the input content. This discrepancy allows an attacker to i...

EUVD-2026-115354

CrewAI contains an SSRF vulnerability caused by its SSRF guard and HTTP client, which both miss malicious content in URLs by checking opposite content passed to it, enabling any request that injects a malicious URL to perform SSRF, such as with the ScrapWebsiteTool...

CVE-2026-120630: CrewAI: CrewAI contains an SSRF vulnerability caused by its SSRF guard and HTTP client, which both miss malicious content in…

CrewAI contains an SSRF vulnerability caused by its SSRF guard and HTTP client, which both miss malicious content in URLs by checking opposite content passed to it, enabling any request that injects a malicious URL to perform SSRF, such as with the ScrapWebsiteTool...

PT-2026-135549

CrewAI contains an SSRF vulnerability caused by its SSRF guard and HTTP client, which both miss malicious content in URLs by checking opposite content passed to it, enabling any request that injects a malicious URL to perform SSRF, such as with the ScrapWebsiteTool...

chat-with-mlx (>=0.1.0, <=0.1.11), crewai-files (>=1.9.0, <=1.10.1a1) +9 more potentially affected by CVE-2026-119203 via pypdf (4.0.2)

pypdf PYPI version 4.0.2 is affected by a known vulnerability. The following packages have a transitive dependency on pypdf and may be impacted: - chat-with-mlx =0.1.0, =1.9.0, =3.2.0, =1.2.1, =1.0.9, =0.0.0, =0.1.2, =0.73.0, =0.94.0 Source cves: CVE-2026-119203 Source advisory:...

chat-with-mlx (>=0.1.0, <=0.1.11), crewai-files (>=1.9.0, <=1.10.1a1) +9 more potentially affected by CVE-2026-119204 via pypdf (4.0.2)

pypdf PYPI version 4.0.2 is affected by a known vulnerability. The following packages have a transitive dependency on pypdf and may be impacted: - chat-with-mlx =0.1.0, =1.9.0, =3.2.0, =1.2.1, =1.0.9, =0.0.0, =0.1.2, =0.73.0, =0.94.0 Source cves: CVE-2026-119204 Source advisory:...

chat-with-mlx (>=0.1.0, <=0.1.11), crewai-files (>=1.9.0, <=1.10.1a1) +9 more potentially affected by CVE-2026-119205 via pypdf (4.0.2)

pypdf PYPI version 4.0.2 is affected by a known vulnerability. The following packages have a transitive dependency on pypdf and may be impacted: - chat-with-mlx =0.1.0, =1.9.0, =3.2.0, =1.2.1, =1.0.9, =0.0.0, =0.1.2, =0.73.0, =0.94.0 Source cves: CVE-2026-119205 Source advisory:...

crewai (>=0.61.0, <=0.70.1), giga-agent (>=0.1.3, <=0.1.9) +3 more potentially affected by CVE-2026-116575 via mem0ai (0.1.115)

mem0ai PYPI version 0.1.115 is affected by a known vulnerability. The following packages have a transitive dependency on mem0ai and may be impacted: - crewai =0.61.0, =0.1.3, =0.1.1, =0.1.1, =2.0.0 Source cves: CVE-2026-116575 Source advisory: OSV:GHSA-5324-3W58-QPP2...

MLflow CrewAI Autologging Records LLM Provider API Keys In Logged Trace Spans

Summary "mlflow.crewai.autolog" leaks CrewAI LLM provider API keys into MLflow trace telemetry. When a CrewAI "Agent" is instrumented with MLflow autologging, MLflow serializes the agent's "dict" and converts its fields to strings. The "llm" field contains the CrewAI LLM object, whose string...

GHSA-J7QQ-VR8C-XVW3 MLflow CrewAI autologging records LLM provider API keys in logged trace spans

Summary mlflow.crewai.autolog leaks CrewAI LLM provider API keys into MLflow trace telemetry. When a CrewAI Agent is instrumented with MLflow autologging, MLflow serializes the agent's dict and converts its fields to strings. The llm field contains the CrewAI LLM object, whose string representati...

MLflow CrewAI autologging records LLM provider API keys in logged trace spans

Summary mlflow.crewai.autolog leaks CrewAI LLM provider API keys into MLflow trace telemetry. When a CrewAI Agent is instrumented with MLflow autologging, MLflow serializes the agent's dict and converts its fields to strings. The llm field contains the CrewAI LLM object, whose string representati...

CVE-2026-116691 MLflow CrewAI autologging records LLM provider API keys in logged trace spans

MLflow is an open source AI engineering platform for agents, large language models, and machine learning models. From 2.19.0 until 3.17.0, mlflow.crewai.autolog records CrewAI Agent objects without consistently sanitizing nested credential-bearing values...

CVE-2026-116691 MLflow CrewAI autologging records LLM provider API keys in logged trace spans

MLflow is an open source AI engineering platform for agents, large language models, and machine learning models. From 2.19.0 until 3.17.0, mlflow.crewai.autolog records CrewAI Agent objects without consistently sanitizing nested credential-bearing values...

CVE-2026-116691 MLflow CrewAI autologging records LLM provider API keys in logged trace spans

MLflow is an open source AI engineering platform for agents, large language models, and machine learning models. From 2.19.0 until 3.17.0, mlflow.crewai.autolog records CrewAI Agent objects without consistently sanitizing nested credential-bearing values...

CVE-2026-116691

The MLflow AI engineering platform is vulnerable in versions 2.19.0 through 3.17.0 due to insufficient sanitization of nested credentials during autologging. Specifically, the mlflow.crewai.autolog() function fails to scrub credential-bearing values when recording CrewAI Agent objects. The functi...

EUVD-2026-111381

MLflow is an open source AI engineering platform for agents, large language models, and machine learning models. From 2.19.0 until 3.17.0, mlflow.crewai.autolog records CrewAI Agent objects without consistently sanitizing nested credential-bearing values...