Agent skills package instructions, scripts, and resources for specialized tasks and are increasingly distributed through public Web repositories. However, existing skill benchmarks primarily focus on downstream task execution, insufficiently assessing specification quality, behavioral robustness, semantic alignment, an...
Meng-Yu Sun, Zun-Long Zhou, Zi-Yuan Yang et al.· 0 citations
It is found that directly composing benign skills can already induce malicious behaviors, even when every individual skill passes security vetting, and some target malicious behaviors remain difficult to realize through direct composition, even when the selected skills collectively provide the required capabilities.
Zun-Long Zhou, Zi-Yuan Yang, Meng-Yu Sun et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.