{"id":"https://openalex.org/W7214027680","doi":"https://doi.org/10.48550/arxiv.2609.22664","title":"From Capability to Assurance in Autonomous Penetration-Testing Harnesses: A Framework and Reference Implementation","display_name":"From Capability to Assurance in Autonomous Penetration-Testing Harnesses: A Framework and Reference Implementation","publication_year":2026,"publication_date":"2026-09-19","ids":{"openalex":"https://openalex.org/W7214027680","doi":"https://doi.org/10.48550/arxiv.2609.22664"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.22664","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.22664","pdf_url":"https://arxiv.org/pdf/2609.22664","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.22664","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013129436","display_name":"Joas Antonio dos Santos","orcid":"https://orcid.org/0009-0003-1772-9826","observed_orcids":["https://orcid.org/0009-0003-1772-9826","https://orcid.org/0009-0001-1148-2186"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Barbosa, Joas Antonio dos Santos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5013129436"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12479","display_name":"Web Application Security Vulnerabilities","score":0.44040000438690186,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12479","display_name":"Web Application Security Vulnerabilities","score":0.44040000438690186,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.1973000019788742,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11424","display_name":"Security and Verification in Computing","score":0.12729999423027039,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/llm-based-agents","display_name":"LLM agents","score":0.8840000033378601},{"id":"https://openalex.org/keywords/penetration-testing","display_name":"penetration testing","score":0.8379999995231628},{"id":"https://openalex.org/keywords/capability-based-security","display_name":"capability-based security","score":0.5899999737739563},{"id":"https://openalex.org/keywords/evidence-grounding","display_name":"evidence grounding","score":0.6489999890327454},{"id":"https://openalex.org/keywords/severity-scores","display_name":"severity scoring","score":0.5569999814033508},{"id":"https://openalex.org/keywords/tamper-evident-logging","display_name":"tamper-evident logging","score":0.8119999766349792},{"id":"https://openalex.org/keywords/software-provenance","display_name":"software provenance","score":0.9190000295639038},{"id":"https://openalex.org/keywords/auditability","display_name":"auditability","score":0.7710000276565552},{"id":"https://openalex.org/keywords/cochise","display_name":"Cochise","score":0.7870000004768372}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6589000225067139},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4255000054836273},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4239000082015991},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.414900004863739},{"id":"https://openalex.org/C2776543023","wikidata":"https://www.wikidata.org/wiki/Q2147046","display_name":"Rework","level":2,"score":0.4108999967575073},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.40369999408721924},{"id":"https://openalex.org/C2779010991","wikidata":"https://www.wikidata.org/wiki/Q2720909","display_name":"Artifact (error)","level":2,"score":0.4027999937534332},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.38530001044273376},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.38370001316070557},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.38269999623298645},{"id":"https://openalex.org/C98184364","wikidata":"https://www.wikidata.org/wiki/Q1780131","display_name":"Argument (complex analysis)","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C2779777834","wikidata":"https://www.wikidata.org/wiki/Q4202277","display_name":"Enforcement","level":2,"score":0.3605000078678131},{"id":"https://openalex.org/C108759981","wikidata":"https://www.wikidata.org/wiki/Q788590","display_name":"Authorization","level":2,"score":0.34869998693466187},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C153180980","wikidata":"https://www.wikidata.org/wiki/Q19776675","display_name":"Commit","level":2,"score":0.3353999853134155},{"id":"https://openalex.org/C2985583900","wikidata":"https://www.wikidata.org/wiki/Q722617","display_name":"Formal description","level":2,"score":0.3312999904155731},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C106436119","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assurance","level":3,"score":0.3140000104904175},{"id":"https://openalex.org/C75606506","wikidata":"https://www.wikidata.org/wiki/Q1049183","display_name":"Formal methods","level":2,"score":0.3125},{"id":"https://openalex.org/C111498074","wikidata":"https://www.wikidata.org/wiki/Q173326","display_name":"Formal verification","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C2778134712","wikidata":"https://www.wikidata.org/wiki/Q1047307","display_name":"Bundle","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.2980000078678131},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C130440534","wikidata":"https://www.wikidata.org/wiki/Q14946528","display_name":"Conflation","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.26759999990463257},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26440000534057617},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2639999985694885},{"id":"https://openalex.org/C71889745","wikidata":"https://www.wikidata.org/wiki/Q1783264","display_name":"Counterfactual conditional","level":3,"score":0.26100000739097595},{"id":"https://openalex.org/C149091818","wikidata":"https://www.wikidata.org/wiki/Q2429814","display_name":"Software system","level":3,"score":0.2517000138759613}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.22664","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.22664","pdf_url":"https://arxiv.org/pdf/2609.22664","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.22664","doi":"https://doi.org/10.48550/arxiv.2609.22664","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.22664","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.22664","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.22664","pdf_url":"https://arxiv.org/pdf/2609.22664","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214027680.pdf","grobid_xml":"https://content.openalex.org/works/W7214027680.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W4385848840","https://openalex.org/W4391800306","https://openalex.org/W4394838745","https://openalex.org/W4402502904","https://openalex.org/W4414450063","https://openalex.org/W4414991283","https://openalex.org/W4415314082","https://openalex.org/W4416242176","https://openalex.org/W4417467403","https://openalex.org/W6929367636","https://openalex.org/W7115599674","https://openalex.org/W7116050802","https://openalex.org/W7140102743","https://openalex.org/W7161046887","https://openalex.org/W7161056873"],"related_works":["https://openalex.org/W7171855721","https://openalex.org/W7172538980","https://openalex.org/W7211984205","https://openalex.org/W7212697485","https://openalex.org/W7163684208","https://openalex.org/W7214383619","https://openalex.org/W7203475415","https://openalex.org/W6968780041","https://openalex.org/W7222108877","https://openalex.org/W6929367636"],"abstract_inverted_index":{"Research":[0],"on":[1,35],"large":[2],"language":[3],"model":[4,130],"agents":[5],"for":[6],"penetration":[7],"testing":[8],"is":[9,33,55],"evaluated":[10],"almost":[11],"entirely":[12],"by":[13,234],"capability:":[14],"whether":[15,40,51,57,66],"the":[16,36,58,85,87,90,156,162,167,215,248,261,272],"agent":[17,43,59],"captures":[18],"a":[19,23,30,52,106,128,175,199,205,208,227,254],"flag":[20],"or":[21],"reproduces":[22],"proof":[24],"of":[25,108],"concept.":[26],"That":[27],"metric":[28],"suits":[29],"benchmark":[31],"but":[32],"silent":[34],"properties":[37,78,111,237,249],"that":[38,81,247],"decide":[39],"an":[41,48,67,132,189,243],"autonomous":[42],"can":[44,69,93],"be":[45,94],"used":[46],"in":[47,96,140],"authorized":[49,63],"engagement:":[50],"reported":[53],"finding":[54],"true,":[56],"stayed":[60],"inside":[61],"its":[62,193,195],"scope,":[64],"and":[65,79,92,122,131,147,161,173,198,218,223,225,258,265],"operator":[68],"audit":[70,219],"what":[71],"it":[72],"did.":[73],"We":[74,213,240],"call":[75],"these":[76],"assurance":[77,110,177],"argue":[80],"they":[82],"belong":[83],"to":[84,137,188,270],"harness,":[86,159],"runtime":[88],"wrapping":[89],"model,":[91],"enforced":[95,120],"code.":[97],"This":[98],"paper":[99],"makes":[100],"three":[101],"contributions.":[102],"First,":[103],"we":[104,151,180,232,259],"define":[105],"framework":[107,168,273],"five":[109],"(evidence":[112],"grounding,":[113],"non":[114],"destructive":[115],"claim":[116,242],"reduction,":[117],"computed":[118],"severity,":[119],"authorization,":[121],"tamper":[123,144],"evident":[124,145],"accountability),":[125],"each":[126],"with":[127],"formal":[129],"explicit":[133],"acceptance":[134,220],"test,":[135],"connected":[136],"prior":[138],"work":[139],"capability":[141],"based":[142],"security,":[143],"logging,":[146],"software":[148],"provenance.":[149],"Second,":[150],"position":[152],"representative":[153],"systems":[154],"(PentestGPT,":[155],"Cochise":[157],"reference":[158],"MAPTA,":[160],"trajectory":[163],"judge":[164],"PentestJudge)":[165],"within":[166],"using":[169],"published":[170],"coding":[171],"criteria,":[172],"identify":[174],"consistent":[176],"gap.":[178],"Third,":[179],"study":[181],"one":[182],"open":[183],"source":[184],"implementation,":[185],"NeuroSploit,":[186],"pinned":[187],"exact":[190],"commit,":[191],"reporting":[192],"architecture,":[194],"complexity":[196],"cost,":[197],"content":[200],"addressed":[201],"artifact":[202],"bundle":[203],"from":[204],"run":[206],"against":[207],"public":[209],"deliberately":[210],"vulnerable":[211],"target.":[212],"execute":[214],"deterministic":[216],"authorization":[217],"tests":[221],"directly":[222],"find":[224],"report":[226],"real":[228],"enforcement":[229],"gap,":[230],"which":[231],"reflect":[233],"scoring":[235],"both":[236],"as":[238],"partial.":[239],"therefore":[241],"initial":[244],"existence":[245],"argument":[246],"are":[250],"realizable":[251],"together,":[252],"not":[253],"comparative":[255],"performance":[256],"result,":[257],"specify":[260],"multi":[262],"target,":[263],"ablation,":[264],"adversarial":[266],"evaluation":[267],"protocol":[268],"required":[269],"turn":[271],"obligations":[274],"into":[275],"measurements.":[276]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-23T00:00:00"}