{"paper":{"title":"Scanning the Harness: An Empirical Study of Supply-Chain Defects in AI Coding-Agent Configurations","arxiv_id":"2609.07360","primary_cat":"cs.SE","submitted_at":"2026-09-07T11:27:24+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":1.0,"id":"s0","own":false,"role":"background","text":"AI coding agents such as Claude Code, Cursor, GitHub Copilot, and OpenAI Codex are configured through artifacts developers write and share: instruction files, skills, hooks, MCP server declarations, subagents.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.07,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.07,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":1.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":0.92,"id":"s1","own":false,"role":"background","text":"This harness is a dependency layer installed from marketplaces and public repositories, running with the developer's privileges, with no lockfile, no install-time check, and no vocabulary for what a component may do.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.13,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.07,"method":0.0,"result":0.0,"background":0.92,"limitation":0.0,"future_work":0.0,"contribution":0.01,"interpretation":0.0}},{"i":2,"p":0.85,"id":"s2","own":true,"role":"method","text":"We study it over 3,171 public GitHub repositories: 2,660 setups that assemble two or more component types and 511 published skill collections.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.92,"main_claim_p":0.03,"quantitative":true,"quantitative_p":0.98,"role_probabilities":{"gap":0.0,"method":0.85,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.15,"interpretation":0.0}},{"i":3,"p":1.0,"id":"s3","own":true,"role":"method","text":"We measure only rules decidable from bytes whose consequence is a security exposure, a configuration that cannot work, or a departure from the Agent Skills specification, and validate every finding before it counts: an independent implementation re-derives it from the repository at its pinned commit, a language-model adjudicator with a released prompt rules on every disagreement, and a second independent model session re-checks every counted pair.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.96,"main_claim_p":0.05,"quantitative":true,"quantitative_p":0.56,"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}},{"i":4,"p":1.0,"id":"s4","own":true,"role":"result","text":"Three security classes survive: 9.8% of setups install an MCP server with no version pinned, 3.1% pre-approve arbitrary execution behind a scoped-looking grant such as Bash(python:*), and 3.8% carry a skill that pre-approves the shell for whoever installs it.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.96,"main_claim_p":0.31,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.0,"result":1.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":5,"p":1.0,"id":"s5","own":true,"role":"result","text":"In total 16.0% of setups carry a security defect and 16.7% a confirmed defect of any kind, against a raw scanner rate of 25.5% on the same rules; the third class ships inside 3.7% of collections, where a marketplace scan can see it.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.96,"main_claim_p":0.42,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.0,"result":1.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":6,"p":0.64,"id":"s6","own":true,"role":"limitation","text":"Rules that compare two files detect differences that are usually intended and are reported as observations.","hedge":{"p":0.87,"label":"asserted"},"own_p":0.86,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.14,"role_probabilities":{"gap":0.0,"method":0.07,"result":0.21,"background":0.0,"limitation":0.64,"future_work":0.0,"contribution":0.0,"interpretation":0.08}},{"i":7,"p":0.99,"id":"s7","own":true,"role":"result","text":"No credential-exfiltration path was confirmed.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.92,"main_claim_p":0.07,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.99,"background":0.0,"limitation":0.01,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":8,"p":0.84,"id":"s8","own":true,"role":"contribution","text":"The instrument, corpus manifest, prompt, and every verdict are released.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.83,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.02,"role_probabilities":{"gap":0.0,"method":0.15,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.01,"contribution":0.84,"interpretation":0.0}}]},"compiled":{"main_claim":{"p":0.98,"text":"In total 16.0% of setups carry a security defect and 16.7% a confirmed defect of any kind, against a raw scanner rate of 25.5% on the same rules; the third class ships inside 3.7% of collections, where a marketplace scan can see it.","location":"abstract s5","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":7188,"cost_usd_reported":0.0},"compiled_at":"2026-09-23","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.05,"states_limitation":0.91,"human_participants":0.04,"controlled_comparison":0.43,"randomized_assignment":0.02,"states_quantitative_result":0.99,"compares_with_prior_results":0.87,"mentions_code_or_data_availability":0.97},"evidential_basis":{"p":0.58,"value":"analysis of existing data","probabilities":{"argument":0.0,"literature":0.0,"proof_or_derivation":0.0,"analysis_of_existing_data":0.58,"observation_or_experiment":0.41,"simulation_or_computation":0.01}},"contribution_type":{"p":1.0,"value":"empirical study","probabilities":{"review":0.0,"method_or_tool":0.0,"empirical_study":1.0,"simulation_study":0.0,"theoretical_result":0.0,"dataset_or_benchmark":0.0,"position_or_commentary":0.0}},"contribution_statement":{"p":0.64,"text":"We measure only rules decidable from bytes whose consequence is a security exposure, a configuration that cannot work, or a departure from the Agent Skills specification, and validate every finding before it counts: an independent implementation re-derives it from the repository at its pinned commit, a language-model adjudicator with a released prompt rules on every disagreement, and a second independent model session re-checks every counted pair.","location":"abstract s3"}},"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":9,"sentences_in_abstract":9},"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"}}}