SkillSafetyBench shows that localized non-user attacks via skills and artifacts can consistently induce unsafe agent behavior across domains and model backends, independent of user intent.
Findings of the Association for Computational Linguistics: ACL 2024 , pages=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CR 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
ARGUS defends LLM agents from context-aware prompt injections by tracking information provenance and verifying decisions against trustworthy evidence, reducing attack success to 3.8% while retaining 87.5% task utility.
citing papers explorer
-
SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces
SkillSafetyBench shows that localized non-user attacks via skills and artifacts can consistently induce unsafe agent behavior across domains and model backends, independent of user intent.
-
ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection
ARGUS defends LLM agents from context-aware prompt injections by tracking information provenance and verifying decisions against trustworthy evidence, reducing attack success to 3.8% while retaining 87.5% task utility.