When a container-level ErrorHandler is configured (the mitigation for finding 221000), each delivery whose processing throws still permanently consumes one link credit. After initialCredits (default 100) failing messages the receiver's credit reaches zero and the broker stops delivering, leaving the listener silently stalled while isRunning() remains true.
Spring AMQP 4.1.0
Applications that configure their broker connection via RabbitConnectionFactoryBean.setUri("amqps://...") without also calling setUseSSL(true) get TLS encryption with no certificate validation and no hostname verification.
Affected versions:
Spring AMQP 4.0.0 through 4.0.3; 3.2.0 through 3.2.10; 3.1.0 through 3.1.15; 2.4.0 through 2.4.17.
In spring AMQP versions 1.0.0 to
2.4.16 and 3.0.0 to 3.0.9 , allowed list patterns for deserializable class
names were added to Spring AMQP, allowing users to lock down deserialization of
data in messages from untrusted sources; however by default, when no allowed
list was provided, all classes could be deserialized.
Specifically, an application is
vulnerable if
* the
SimpleMessageConverter or SerializerMessageConverter is used
* the user
does not configure allowed list patterns
* untrusted
message originators gain permissions to write messages to the RabbitMQ
broker to send malicious content
In Spring AMQP versions 2.2.0 - 2.2.19 and 2.3.0 - 2.3.11, the Spring AMQP Message object, in its toString() method, will create a new String object from the message body, regardless of its size. This can cause an OOM Error with a large message
In Spring AMQP versions 2.2.0 - 2.2.18 and 2.3.0 - 2.3.10, the Spring AMQP Message object, in its toString() method, will deserialize a body for a message with content type application/x-java-serialized-object. It is possible to construct a malicious java.util.Dictionary object that can cause 100% CPU usage in the application if the toString() method is called.