Metraipolis › archive › dc_5162946bf88d
SkillDRE: Dual-Stage Red-Team Evolution of Agent Skills via Pre-Execution and Runtime Feedback — arXiv:2609.32400
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.32400
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T21:00:10.171Z
- SHA-256 of the archived text
8b9b8954061740225f673cfa7ddf951dc0a80c1d23ff381213923ed71f14930d- Stable URL of this page
https://metraipolis.com/documento/dc_5162946bf88d
How to cite
SkillDRE: Dual-Stage Red-Team Evolution of Agent Skills via Pre-Execution and Runtime Feedback — arXiv:2609.32400 — arXiv (en), https://arxiv.org/abs/2609.32400 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5162946bf88d (Metraipolis archive dc_5162946bf88d, sha256 8b9b8954061740225f673cfa7ddf951dc0a80c1d23ff381213923ed71f14930d)
BibTeX
@misc{dc5162946bf88d,
title = {SkillDRE: Dual-Stage Red-Team Evolution of Agent Skills via Pre-Execution and Runtime Feedback — arXiv:2609.32400},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.32400},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5162946bf88d; sha256 8b9b8954061740225f673cfa7ddf951dc0a80c1d23ff381213923ed71f14930d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32400. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Agent skills package instructions, executable code, and task-specific resources into reusable artifacts that agents can improve using execution feedback. The same mechanism also enables attackers to evolve malicious skills, making them more effective and less detectable. However, a candidate skill may pass pre-execution scanning yet fail to realize its target under runtime defenses, while a revision that repairs execution may introduce new scanner findings. We introduce SkillDRE, a fully automated framework for evolving complete malicious skill packages through a dual-stage feedback loop. Given a benign task and its associated skills, SkillDRE autonomously constructs and validates a task-conditioned malicious objective and a verifiable judge rule. It then holds both fixed while evolving the skill implementation, with preservation of legitimate task capability. SkillDRE combines scanner-guided evolution with runtime-guided refinement informed by execution outcomes observed under runtime defense. Each runtime-guided revision returns to the pre-execution stage for rescanning and further optimization before re-execution, forming a cross-stage closed loop. Evaluated on SkillsBench across four victim models, SkillDRE achieves an average attack success rate of 45.28%, exceeding the strongest baseline by 40.3%, while its final submitted skills receive no SkillScan findings and largely preserve benign-task performance. These results show that two-stage defense feedback can serve as a useful learning signal for adaptive red teaming and that evaluating either defense stage in isolation can miss the resulting attack capability. Codes is available at this https URL Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.32400 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T20:29:02.323Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).