Metraipolis › archive › dc_0d4dcc1de3bd

Behavioral Skill Reconstruction: Reconstructing Hidden Functionality from LLM Agent Skills — arXiv:2608.04192

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.04192
License (as archived)
CC0-1.0
Archived
2026-10-31T11:13:36.993Z
SHA-256 of the archived text
36c5fab029b0e23a2ef86ce8c56394e7b84fd44c7e643a0c5f44407258d16ad9
Stable URL of this page
https://metraipolis.com/documento/dc_0d4dcc1de3bd

How to cite

Behavioral Skill Reconstruction: Reconstructing Hidden Functionality from LLM Agent Skills — arXiv:2608.04192 — arXiv (en), https://arxiv.org/abs/2608.04192 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0d4dcc1de3bd (Metraipolis archive dc_0d4dcc1de3bd, sha256 36c5fab029b0e23a2ef86ce8c56394e7b84fd44c7e643a0c5f44407258d16ad9)
BibTeX
@misc{dc0d4dcc1de3bd,
  title = {Behavioral Skill Reconstruction: Reconstructing Hidden Functionality from LLM Agent Skills — arXiv:2608.04192},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.04192},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0d4dcc1de3bd; sha256 36c5fab029b0e23a2ef86ce8c56394e7b84fd44c7e643a0c5f44407258d16ad9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04192. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Closed source agent skills may encode proprietary instructions, scripts, constants, and data. Providers may offer their capabilities as services while keeping the underlying packages hidden. Prior work focuses on prompt injection attacks that directly disclose these artifacts, and existing defenses accordingly aim to prevent such leakage. However, preventing file disclosure does not prevent users from recovering the functionality those files implement. This raises a fundamental question: can a user reconstruct a skill's functionality through ordinary use while its files remain hidden? We study behavioral skill reconstruction (BSR), in which an attacker uses valid task requests and observed responses to build a functional clone of a hidden skill. We introduce SkillClone, a black-box attack that clones a target skill by forming an interface hypothesis from its public advertisement, issuing structured benign probes, synthesizing an executable replica, and iteratively repairing it through differential validation against the victim skill. Across 30 skills spanning rules, tables, procedures, and algorithms, SkillClone achieves exact or partial recovery on held-out inputs for several targets. Iterative requerying closes gaps missed by single-round reconstruction. Because SkillClone uses only legitimate interactions, disclosure-focused defenses provide limited coverage, and less detailed skill descriptions offer limited protection. These results show that file secrecy alone does not ensure functional secrecy. Defenses must also limit cumulative information leakage from ordinary use.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-06 in cs.AI).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.04192 — 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 2026-10-31T11:02:13.487Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).