SourceJul 8, 20262026-07-084 minVerified
Why Tool-Calling Agent Security Is a Structural Problem
Why text-driven tool calls make AI agent delegation a structural security issue, backed by refusal-rate evidence.
SourceJun 27, 20262026-06-274 minVerified
Why Agent Configs Need Deterministic Control Planes
Why reused coding agent config files can become an unmanaged control layer with security and operational risks.
CommunityJun 18, 20262026-06-185 minVerified
Alignment and Safety Guardrails Shape Model Behavior
Shows with public metrics that alignment and guardrails affect instruction following, harmful output, and hallucination trade-offs.
SourceMay 30, 20262026-05-304 minVerified
DistractionIF Exposes Hidden Instruction Risks In RAG Systems
DistractionIF shows how RAG systems misread instruction-like noise in documents and why pipeline design matters.
SourceMar 27, 20262026-03-275 minVerified
RAG Security Risks From Combined Injection And Poisoning
Examines security risks in RAG when prompt injection and database poisoning combine across retrieval and indexing.
SourceMar 26, 20262026-03-264 minVerified
Execution Provenance Defines Real Agent Security Boundaries
Agent security depends less on benchmark scores than on tracing execution provenance across generation, handoffs, and permissions.
GuideFeb 14, 20262026-02-145 minVerified
Designing Agent Defenses Against Prompt Injection Attacks
How prompt injection rides untrusted content into tool calls, and how to mitigate it with least privilege, sandboxing, fixed schemas, and output validation.
CommunityFeb 2, 20262026-02-024 minVerified
Addressing Steganography Threats and Security Risks in Language Models
Analyzes AI steganography threats where hidden data manipulates models and explores defense strategies like RepreGuard.