References
LLM-based NPCs in Video Games: A Systematic Mapping Study- PerturbAI and OpenAI Unveil First-of-Its-Kind AI Reasoning Agents to Scale Biomedical Discovery
- Using thousands of AI agents to uncover new leads in biological data
- Are Large Pre-Trained Language Models Leaking Your Personal Information?
MCP connectors are not a context engine- InfoQ eMag 123: Securing the AI Stack, From Model to Production
Vercel Security Review
Announcing AWS Well-Architected Agent (preview)- On the (Im)possibility of Obfuscating Programs - Springer Nature
- MLReplicate: Benchmarking Autonomous Research Systems for ...
When prompts become shells: RCE vulnerabilities in AI ...
Evaluating foundation model integration strategies for detecting PII in java software engineering pipelines - Empirical Software EngineeringGuardrails and moderation — Study · AddressHate
- Stealing Reasoning Traces from Proprietary LLM APIs
Red-Teaming Coding Agents from a Tool-Invocation Perspective: An Empirical Security Assessment
Crowdsourced audit of Twitter’s recommender systems - Scientific Reports
Three AI Coding Agents, One GitHub Issue: CI/CD Secrets Exposed- MCP Auto-Execution: AI Coding Assistants and Credential Theft
The Authority Benchmark: do AI agents follow the rules they are given? | Plaw
LFM3 Harness Deep Dive: How a Sub-2B ...
Frontiers | Poisoning-resistant signature sharing for hybrid intrusion detection using a permissioned blockchain ledger
TraceTrial-Bench: How Reliable Are Agent Harnesses Across 3,420 Runs?