ResearchTasksAgentic Workflow Hijacking Vulnerability DetectionFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast Updatedgoogle-github-actions/run-gemini-cliJAW-NoPromptProv6M.P. Score14May 13, 2026ask-bonk GitHub ActionAutoDAN-T7.6M.P.14May 13, 2026qwen-code-action GitHub ActionSearch-based6M.P. Score10May 13, 2026