Skip to content

DEV Community

Agent Safety Engineering Series' Articles

Back to hugginf_expert's Series

Cover image for When Attackers Bring Their Own Agents: A Defensive Gating Playbook

Oct 6

When Attackers Bring Their Own Agents: A Defensive Gating Playbook

#ai #agents #security #llm

7 min read

Cover image for Indirect Prompt Injection Through Tool Descriptions and Tool Output: How Untrusted Metadata Hijacks Agents

Oct 6

Indirect Prompt Injection Through Tool Descriptions and Tool Output: How Untrusted Metadata Hijacks Agents

#ai #agents #security #llm

7 min read

Oct 12

Action Safety for Agents: Deciding What an Agent Is Allowed to Do

#ai #machinelearning #llm #security

3 min read

Cover image for Your Agent's Gate Threshold Is a Winner's Curse: Tuning Per-Action Thresholds Without Fooling Yourself

Oct 19

Your Agent's Gate Threshold Is a Winner's Curse: Tuning Per-Action Thresholds Without Fooling Yourself

#ai #machinelearning #security #agents

13 min read

Cover image for A Guardrail That Cuts Attack Success 10x Can Still Be the Wrong Guardrail: Reading AgentDojo Numbers Like an Engineer

Oct 20

A Guardrail That Cuts Attack Success 10x Can Still Be the Wrong Guardrail: Reading AgentDojo Numbers Like an Engineer

#ai #security #agents #machinelearning

11 min read

Cover image for The Model Is Not a Security Boundary: What Two Semantic Kernel CVEs Teach About Gating Tool Arguments

Oct 21

The Model Is Not a Security Boundary: What Two Semantic Kernel CVEs Teach About Gating Tool Arguments

#ai #python #security #agents

13 min read

Cover image for Training Where the Data Lives: Why On-Prem Training on Inference NPUs Matters for AI Governance

Oct 26

Training Where the Data Lives: Why On-Prem Training on Inference NPUs Matters for AI Governance

#ai #machinelearning #security #privacy

2 min read