Metraipolis › archive › dc_9fe23f7ac690
Approval Laundering: Systematizing Approval--Execution Binding Failures in AI Coding-Agent Harnesses — arXiv:2609.38983
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.38983
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T12:44:42.074Z
- SHA-256 of the archived text
556451dec65529ae132574eee816937673313becb7720d2eab0ebcb27de197c3- Stable URL of this page
https://metraipolis.com/documento/dc_9fe23f7ac690
How to cite
Approval Laundering: Systematizing Approval--Execution Binding Failures in AI Coding-Agent Harnesses — arXiv:2609.38983 — arXiv (en), https://arxiv.org/abs/2609.38983 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9fe23f7ac690 (Metraipolis archive dc_9fe23f7ac690, sha256 556451dec65529ae132574eee816937673313becb7720d2eab0ebcb27de197c3)
BibTeX
@misc{dc9fe23f7ac690,
title = {Approval Laundering: Systematizing Approval--Execution Binding Failures in AI Coding-Agent Harnesses — arXiv:2609.38983},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.38983},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9fe23f7ac690; sha256 556451dec65529ae132574eee816937673313becb7720d2eab0ebcb27de197c3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38983. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Modern AI coding-agent harnesses (Claude Code, Codex CLI, Cursor) rest their security boundary on a largely unexamined assumption: that the action A a human approves is the same action A' the harness executes, where A is fixed by a stated policy for what a scope grant or session-scoped approval authorizes. We show this assumption fails systematically and reproducibly. We introduce Approval Laundering, a taxonomy of six failure modes by which a harness's enforcement mechanism silently substitutes A' for A after approval: Scope, Argument, Temporal, Tool, Delegation, and Semantic laundering. Unlike prior work that evaluates risk classifiers against static corpora or infers implicit authorization boundaries, we study credential-binding integrity: given an already-approved action, does the harness dispatch exactly that action? Instrumenting Claude Code's pre-execution mediation point (PreToolUse), we conduct a controlled, headless, repeated-measures study of all six classes (N=19-20 runs each), reporting a Bound-Gap Rate (BGR) with Wilson confidence intervals and inter-rater agreement (kappa=1.0). We prototype Approval Token, a keyed capability Hk(principal, agent_id, session_id, tool, arguments, scope, expiry) issued by a mediator that never returns the key to the agent, evaluated via paired before/after replay of 118 runs (McNemar's exact test). The token fully eliminates Delegation laundering and, for our seeded session-identity-mismatch construction, Temporal laundering (p<10^-5), but by design leaves Scope laundering unaffected and shows no significant reduction in Argument laundering (p=1): an honest negative result, since these two classes leave every recorded dispatch field unchanged, diverging one process level below what a field-only verifier can observe. We discuss implications for defenses that bind only at the tool-invocation boundary. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.AI). Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI); Software Engineering (cs.SE). Pagina del lavoro: https://arxiv.org/abs/2609.38983 — 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 2026-10-07T12:14:13.990Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).