Impact
Security research involving model-output integrity and reliability
62 matching entries out of 539 in this category
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.
Self-evolving agent-skill systems may promote recurring, attacker-controlled execution records into persistent reusable instructions. The paper evaluates whether poisoned but task-plausible trajectories survive aggregation and appear in generated skill artifacts, using inert canary behaviors and two structurally different skill-evolution pipelines.
SkillSentry evaluates third-party agent skills by constructing source-grounded decoy environments and comparing matched executions with and without the tested skill. The method requires completed, observable, skill-attributed side effects rather than treating suspicious text, ordinary privileged operations, or unexecuted paths as proven malicious behavior.
Third-party fine-tuning adapters may contain backdoors. Z-PEFT screens adapter weights using spectral features, evaluated on PADBench's 13,300 adapters.
VulnGym measures whether coding agents can locate and explain repository-level security vulnerabilities from realistic advisory and source-code context. The benchmark contains 184 reviewed advisories, 408 line-annotated vulnerability entries, and 23 repositories, with separate end-to-end detection and oracle-conditioned localization tasks.
MemSecBench follows malicious agent-memory content from initial write through persistence, retrieval, action selection, execution, and attempted selective repair. Its controlled Write–Execute–Forget protocol evaluates 310 human-reviewed cases across two harnesses, four memory backends, three model backends, and seven evidence-gated lifecycle checkpoints.
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.
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.
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.
Shell-command screening can miss harmful actions generated by coding agents. CARE combines static checks with optional model review at the command-dispatch boundary.