Metraipolis › archive › dc_c21deeae1e02

RuntimeTickets: Source-Grounded Security Obligations for Agent Skills — arXiv:2611.03772

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.03772
License (as archived)
CC0-1.0
Archived
2026-11-04T12:29:28.130Z
SHA-256 of the archived text
c347024bbc77ffdcae9841e24ec46308753e6eca8a98ef1192fa835571156d92
Stable URL of this page
https://metraipolis.com/documento/dc_c21deeae1e02

How to cite

RuntimeTickets: Source-Grounded Security Obligations for Agent Skills — arXiv:2611.03772 — arXiv (en), https://arxiv.org/abs/2611.03772 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c21deeae1e02 (Metraipolis archive dc_c21deeae1e02, sha256 c347024bbc77ffdcae9841e24ec46308753e6eca8a98ef1192fa835571156d92)
BibTeX
@misc{dcc21deeae1e02,
  title = {RuntimeTickets: Source-Grounded Security Obligations for Agent Skills — arXiv:2611.03772},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.03772},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c21deeae1e02; sha256 c347024bbc77ffdcae9841e24ec46308753e6eca8a98ef1192fa835571156d92},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03772. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Third-party Agent Skills extend what an autonomous agent can do, but a malicious Skill can hide data exposure or output manipulation inside a legitimate workflow. Neither reading a Skill's description nor granting it tool permissions tells whether its execution meets the user's security requirements. We introduce RuntimeTickets, a protocol that enforces and audits these requirements while a Skill runs. From released malicious-Skill datasets we derive a risk model and build adversarial-benign Skill pairs. From the task's delivery contract, a language model proposes security obligations for that task. Each obligation cites the Skill lines it answers, and the ticket tightens the host's approvals into fine-grained allowed actions but never loosens them. A runtime gate checks the recipient, object and amount of every outbound send before forwarding it, and trusted monitors record the effects within their observation scope. The ticket links these checks and observations to the approved obligations of each Skill run, and a deterministic decoder turns the ticket's status into governable data flows and verifies each obligation. Neither enforcement nor decoding involves a language model, so text injected by a Skill can change the proposal but never the rule that decides a send. We evaluate RuntimeTickets at the network egress boundary of three unmodified agent frameworks against production Skill scanners and runtime baselines, among them an AgentBound-derived allow-list and SkillGuard. RuntimeTickets eliminated both failure modes of current Skill defenses, overlook (malicious Skills let through) and overkill (benign Skills blocked): its overlook rate was 0.0% and its overkill rate 0.0%, while the scanners erred on both sides. RuntimeTickets ties approved requirements to verifiable execution evidence and offers a common foundation for the safe and auditable deployment of third-party Skills.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.03772 — 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 2026-11-04T12:26:47.224Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).