Explore primary-source AI security research, evaluated models, attack techniques, and defensive evidence.
985 research findings · 1119 evaluated models
Matches every word across titles, descriptions, sources, affected systems, and models.
API gateways can pool distinct customers into one upstream cache identity. The authors observe cross-customer cache reuse in five deliberately pooled gateway configurations through two provider interfaces.
The authors report historical isolation failures in client-held encrypted reasoning blocks across compatible provider API contexts.
Lower-trust tool content can assert facts beyond its authority and distort an agent's decisions. PIPES screens response units against source provenance and expected field meaning.
Third-party fine-tuning adapters may contain backdoors. Z-PEFT screens adapter weights using spectral features, evaluated on PADBench's 13,300 adapters.
Shell-command screening can miss harmful actions generated by coding agents. CARE combines static checks with optional model review at the command-dispatch boundary.
Untrusted issue descriptions and tool responses can redirect privileged coding and tool agents. Twin Agent separates exploration from execution and restricts the information exchanged between them.
AgentS4D measures unsafe actions and state changes across complete workspace-agent executions rather than treating task completion or isolated model responses as safety evidence. Its 328 sandboxed cases introduce risky content through user requests, documents, web resources, tools, third-party skills, and persistent memory, then compare the same cases across four agent harnesses and five model backends.
OpenSkillRisk evaluates whether agent harnesses safely handle third-party skills that introduce risky behavior through otherwise plausible, benign tasks. The benchmark assembles 263 risky skills from public agent-skill ecosystems and tests three CLI-agent harnesses against seven risk categories using isolated task workspaces, mocked external services, and execution-level evidence.
IssueTrojanBench studies indirect prompt injection when a coding agent processes an apparently ordinary software-development issue or related artifact. Starting with six legitimate seed issues from two Python repositories, the authors construct 696 adversarial issue variants spanning four unsafe-action families and six delivery formats, then execute those variants across six agent-model configurations.
HANDBOOK.md measures whether an agent can apply detailed organizational rules while completing realistic, multi-step enterprise tasks. The vendor-authored benchmark includes 65 resettable MCP-backed workflows, policy documents of 20 to 124 pages, and 824 deterministic rubric checks covering required decisions, prohibited actions, and final environment state.
Entries summarize publicly available primary-source security research. Model names reflect only systems explicitly evaluated by the cited paper, and measurements are research-reported unless independent verification is stated.
Discovery and publication are separate: new papers enter a candidate queue, then require human review and explicit approval before publication. Updates follow that review process, not a guaranteed daily publishing schedule. “Last analyzed” is the newest analysis date among published entries; it does not mean that all recent research has been covered.