Agent Security
AI Agent Pentesting Tools Compared for Agentic Architectures
Static pentesting tools miss the real threats in AI agents.
Lucia Bennett
Columnist · · 11 min read
ThreatIntel Review — Page 2
Isolated Twin Environments for Agent Security Testing
Isolated twin environments catch multi-layer attacks that point-in-time testing structurally misses.
Leila Bauer
Supply Chain Risk in Third-Party MCP Tool Integrations
Tool definitions stay mutable after approval, turning runtime trust into a security vulnerability.
Leila Sørensen
Prompt Injection via Workspace Content in AI IDE Agents
Attackers hide commands in files agents must read to work.
Selin Nakamura
OWASP Agentic Top 10 Applied to Production Deployments
Real agents with real credentials demand controls that survive when the model's goals get hijacked.
Estelle Haddad
Reconnaissance Techniques Targeting Deployed AI Agents
Attackers map AI agents' capabilities, memory, and boundaries before exploiting them.
Malik Osei
AI Agent Attack Surface Differences From Traditional API Threats
Agents expose attackers to trust boundaries that form at runtime, not design time.
Nico Halvorsen
Indirect Prompt Injection in Agentic Retrieval Pipelines
Attackers exploit agentic systems by embedding malicious instructions in content agents retrieve.
Simone Wexler