Skip to content
Threat Feed
Subscribe

Tag

Guardrails

3 briefs RSS
critical advisory

Arbitrary XML Schema Definition Processing in guardrails-detectors Leads to SSRF and Local File Read

A flaw in the 'file_type' content detector of 'guardrails-detectors' allows a remote attacker to provide an arbitrary XML Schema Definition (XSD) string, leading to server-side request forgery (SSRF) and local file reads, potentially exposing sensitive information such as cloud provider credentials or granting access to internal network services.

guardrails-detectors vulnerability ssrf local-file-read info-disclosure guardrails
3t 1c
high advisory

CrowdStrike Falcon AIDR Supports NVIDIA NeMo Guardrails for AI Agent Protection

CrowdStrike Falcon AIDR now supports NVIDIA NeMo Guardrails (v0.20.0) to protect AI agents from prompt injection, data exposure, and unauthorized actions, enabling safer deployment of AI applications.

ai-security prompt-injection data-protection guardrails agentic-ai
2r 6t
high advisory

AWS Bedrock GuardRails Deletion Attempt

Detection of attempts to delete AWS Bedrock GuardRails, security controls that prevent harmful AI outputs, via the DeleteGuardrail API in AWS CloudTrail logs, potentially indicating an adversary attempting to remove these safeguards after compromising credentials to manipulate model behavior for malicious purposes.

AWS Bedrock aws bedrock guardrails defense-evasion cloud
2r 1t