
Agentic-Evidence
OWASP reference project for agentic AI security evidence: correlates agent execution, identity, tool calls, and authorization decisions into…
ai-securityanomaly-detectioncurated-resources+6

OWASP reference project for agentic AI security evidence: correlates agent execution, identity, tool calls, and authorization decisions into…

An audit-oriented risk model for how agent-generated inferences can change epistemic status, gain operational authority, and influence later…

Open .eml test set for evaluating how email security controls and AI mailbox assistants handle indirect prompt injection across disclosure,…

LLM safety: analyze how fine-tuning shifts refusal behavior and evaluate layer-freezing and low-rank defenses.

Fix-Like Artifacts With Embedded Defects