26.1% of analyzed AI agent skills contain vulnerabilities across 14 patterns, with executable scripts raising risk 2.12x, based on static and LLM analysis of 31k skills.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CR 3representative citing papers
JBShield is vulnerable to adaptive JB-GCG attacks (up to 53% ASR) because jailbreak representations occupy a distinct region in refusal-direction space; the new RTV defense using Mahalanobis detection on multi-layer fingerprints reaches 0.99 AUROC and limits adaptive ASR to 7%.
ASTRA is an automated closed-loop framework that discovers, retrieves, and evolves jailbreak attack strategies for LLMs using a dynamic three-tier strategy library and outperforms baselines in black-box settings.
citing papers explorer
-
Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale
26.1% of analyzed AI agent skills contain vulnerabilities across 14 patterns, with executable scripts raising risk 2.12x, based on static and LLM analysis of 31k skills.
-
Revisiting JBShield: Breaking and Rebuilding Representation-Level Jailbreak Defenses
JBShield is vulnerable to adaptive JB-GCG attacks (up to 53% ASR) because jailbreak representations occupy a distinct region in refusal-direction space; the new RTV defense using Mahalanobis detection on multi-layer fingerprints reaches 0.99 AUROC and limits adaptive ASR to 7%.
-
ASTRA: An Automated Framework for Strategy Discovery, Retrieval, and Evolution for Jailbreaking LLMs
ASTRA is an automated closed-loop framework that discovers, retrieves, and evolves jailbreak attack strategies for LLMs using a dynamic three-tier strategy library and outperforms baselines in black-box settings.