{"paper":{"title":"CreepScope: Measuring Post-Use Authorization Exposure in Tool-Using Agents","arxiv_id":"2610.15988","primary_cat":"cs.CR","submitted_at":"2026-10-11T23:39:44+00:00","version_compiled":"v1"},"notice":"Every quoted sentence is the authors' text from the arXiv listing abstract. Labels and probabilities are the outputs of classifier-1.13.0 on the question bank abstract-p1-20260923, exactly as returned. No sentence in this record was written by a language model.","schema":"pith.compiled-record/v0","status":"compiled","abstract":{"source":"arXiv listing abstract v1","sentences":[{"i":0,"p":0.79,"id":"s0","own":false,"role":"gap","text":"Authorization checks at individual tool calls do not reveal how long earlier authority remains usable.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.11,"main_claim_p":0.07,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.79,"method":0.0,"result":0.0,"background":0.21,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":0.45,"id":"s1","own":false,"role":"background","text":"We study this lifecycle failure as privilege creep: a capability stays reachable after its last justified workflow step.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.21,"main_claim_p":0.09,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.23,"method":0.0,"result":0.0,"background":0.45,"limitation":0.0,"future_work":0.0,"contribution":0.31,"interpretation":0.01}},{"i":2,"p":0.64,"id":"s2","own":true,"role":"contribution","text":"We present CreepScope, a trace-oriented evaluation protocol that samples reachable authority at every step and separates no-remaining-use exposure into stale-after-use and never-required components; Capability-Step Exposure (CSE) counts total stepwise overexposure and Residual Privilege Debt (RPD) the terminal residue, while stale-after-use exposure is the direct privilege-creep measure.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.92,"main_claim_p":0.16,"quantitative":false,"quantitative_p":0.07,"role_probabilities":{"gap":0.0,"method":0.36,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.64,"interpretation":0.0}},{"i":3,"p":0.95,"id":"s3","own":true,"role":"result","text":"A 96-cell deterministic replay over 12 controlled storage, communication, and cloud-operation workflows validates these semantics: Static Task Scope and Monotonic On-Demand retain mean CSEs of 26 and 13, whereas an oracle-controlled Step Lease has zero CSE and zero residual debt by construction.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.96,"main_claim_p":0.17,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.04,"result":0.95,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.01,"interpretation":0.0}},{"i":4,"p":0.57,"id":"s4","own":true,"role":"result","text":"All three persistent regimes share the same stale-after-use exposure of 13, so their CSE differences come from scope and grant timing rather than post-use retention; Full Access alone adds 91.33 never-required capability-steps.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.94,"main_claim_p":0.19,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.57,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.43}},{"i":5,"p":0.98,"id":"s5","own":true,"role":"result","text":"A separate 24-episode local case then lets Qwen2 7B choose tools in one simulated mail workflow: the injected stale send executes in all nine persistent-policy episodes and in none of the three Step-Lease episodes, while all 24 required action sequences complete.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.94,"main_claim_p":0.15,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.02,"result":0.98,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":6,"p":0.99,"id":"s6","own":true,"role":"limitation","text":"These results establish a reproducible containment case, not cross-workflow or cross-model effectiveness.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.79,"main_claim_p":0.21,"quantitative":false,"quantitative_p":0.06,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":0.0,"limitation":0.99,"future_work":0.0,"contribution":0.0,"interpretation":0.01}},{"i":7,"p":1.0,"id":"s7","own":true,"role":"method","text":"Core metrics are reconstructed from raw events, and exact gates reject incomplete or duplicated evaluation grids.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.89,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.06,"role_probabilities":{"gap":0.0,"method":1.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}}]},"compiled":{"main_claim":{"p":0.51,"text":"These results establish a reproducible containment case, not cross-workflow or cross-model effectiveness.","location":"abstract s6","hedge_strength":{"p":1.0,"label":"asserted"}},"provenance":{"route":{"via":"TypeSafe API","model":"classifier-1.13.0","endpoint":"https://api.typesafe.ai/v1/systemone","provider":"TypeSafe"},"packing":"one request per paper","requests":1,"input_tokens":6482,"cost_usd_reported":0.0},"compiled_at":"2026-10-14","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.07,"states_limitation":0.97,"human_participants":0.03,"controlled_comparison":0.91,"randomized_assignment":0.03,"states_quantitative_result":0.99,"compares_with_prior_results":0.86,"mentions_code_or_data_availability":0.04},"evidential_basis":{"p":0.56,"value":"observation or experiment","probabilities":{"argument":0.0,"literature":0.0,"proof_or_derivation":0.0,"analysis_of_existing_data":0.0,"observation_or_experiment":0.56,"simulation_or_computation":0.44}},"contribution_type":{"p":0.98,"value":"method or tool","probabilities":{"review":0.0,"method_or_tool":0.98,"empirical_study":0.02,"simulation_study":0.0,"theoretical_result":0.0,"dataset_or_benchmark":0.0,"position_or_commentary":0.0}},"contribution_statement":{"p":1.0,"text":"We present CreepScope, a trace-oriented evaluation protocol that samples reachable authority at every step and separates no-remaining-use exposure into stale-after-use and never-required components; Capability-Step Exposure (CSE) counts total stepwise overexposure and Residual Privilege Debt (RPD) the terminal residue, while stale-after-use exposure is the direct privilege-creep measure.","location":"abstract s2"}},"coverage":{"tier":"abstract","levels_run":["P abstract"],"not_examined":["full text","figures and tables","references and citing sentences","relations to other papers"],"sources_read":["arXiv listing abstract v1"],"levels_not_run":["S sections","T body sentences","C citations","R cross-paper relations"],"sentences_examined":8,"sentences_in_abstract":8},"measured_accuracy":{"url":"https://pith.science/accuracy","measured_on":"2026-10-02","method":"two independent model families labelled a fresh random sample blind; the figure is how often the published label matches their consensus","sentence_role_agreement":0.92,"main_claim_agreement":0.908,"typed_citation_agreement":0.933,"typed_citation_agreement_95_interval":[0.917,0.945],"review_comments_accurate":0.758,"review_comments_accurate_95_interval":[0.684,0.82],"review_caught_admitted_error_found_or_related":0.448,"review_comments_judged":{"judged_by":["gpt-5.6-luna","grok-4.7"],"judged_against":"Pith's own text copy of each paper: text extracted from the PDF, the first 90,000 characters","measured_on":"2026-10-04","accurate":113,"decided":149,"sampled_reviews":200,"split_by_lane":false,"by_lane":"https://pith.science/accuracy#by-lane"}}}