MMSkillRisk: יכולות השקיפה של הסקילים: האם הסקילים יכולים להיות בטוחים כאשר יכולות השקיפה ההיקפיות הופכות לפחד?

תקציר מקורי באנגליתarXiv:2609.35912v1 Announce Type: cross Abstract: Agent skills are shareable packages of procedural instructions, tools, and examples. Multimodal skills additionally include visual references that agents retrieve and inspect during execution. Because these images guide actions, attackers can disguise malicious instructions as ordinary visual guidance within otherwise legitimate skills. Existing skill-security research primarily examines text-carried attacks or scanner detection, leaving the runtime effects of image-borne attacks insufficiently evaluated. We introduce MMSkillRisk, to our knowledge the first publicly available benchmark dedicated to end-to-end safety evaluation of image-borne attacks in multimodal skills. To instantiate this attack surface, we design Native-Context Visual At