{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZMOIRMT5EVZJ7NDV7BYIZZFUZ6","short_pith_number":"pith:ZMOIRMT5","schema_version":"1.0","canonical_sha256":"cb1c88b27d25729fb475f8708ce4b4cfb4b297f4fb5242963b9edfb1c4ecfe49","source":{"kind":"arxiv","id":"2607.00481","version":1},"attestation_state":"computed","paper":{"title":"Beyond the Prompt: Jailbreaking Function-Calling LLMs via Simulated Moderation Traces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Haobo Wang, Junlong Liu, Weiqi Luo, Xiaojun Jia","submitted_at":"2026-07-01T06:08:07Z","abstract_excerpt":"Jailbreak attacks remain a critical threat to the safe deployment of large language models (LLMs). While prior work has primarily studied attacks and defenses at the prompt level, we show that this prompt-centric paradigm overlooks a structural vulnerability in stateful, function-calling environments. In such applications, developer-defined schemas, structured arguments, and untrusted tool outputs are interleaved into a single shared model context. This architecture expands the attack surface by blurring the boundary between trusted control logic and untrusted data, allowing adversarial intent"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.00481","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2026-07-01T06:08:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"301a94f4f30dd4b90a94243c004f70ef4ef8d7559df9d488ab61529da088c398","abstract_canon_sha256":"d2500d4fe4380d514921c970e32b42304c11fc6c5ac8dd52336fd18df6bc6a5a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:17:44.617539Z","signature_b64":"ACek6SAV8t31LME7GYVEen6Az9nnAKsXToK51kV9n47WMqozwBRLDGCOb9QFq+auDo57DYH59THYeRJEsBDKDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb1c88b27d25729fb475f8708ce4b4cfb4b297f4fb5242963b9edfb1c4ecfe49","last_reissued_at":"2026-07-02T01:17:44.617141Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:17:44.617141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond the Prompt: Jailbreaking Function-Calling LLMs via Simulated Moderation Traces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Haobo Wang, Junlong Liu, Weiqi Luo, Xiaojun Jia","submitted_at":"2026-07-01T06:08:07Z","abstract_excerpt":"Jailbreak attacks remain a critical threat to the safe deployment of large language models (LLMs). While prior work has primarily studied attacks and defenses at the prompt level, we show that this prompt-centric paradigm overlooks a structural vulnerability in stateful, function-calling environments. In such applications, developer-defined schemas, structured arguments, and untrusted tool outputs are interleaved into a single shared model context. This architecture expands the attack surface by blurring the boundary between trusted control logic and untrusted data, allowing adversarial intent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00481","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.00481/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.00481","created_at":"2026-07-02T01:17:44.617201+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.00481v1","created_at":"2026-07-02T01:17:44.617201+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00481","created_at":"2026-07-02T01:17:44.617201+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZMOIRMT5EVZJ","created_at":"2026-07-02T01:17:44.617201+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZMOIRMT5EVZJ7NDV","created_at":"2026-07-02T01:17:44.617201+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZMOIRMT5","created_at":"2026-07-02T01:17:44.617201+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZMOIRMT5EVZJ7NDV7BYIZZFUZ6","json":"https://pith.science/pith/ZMOIRMT5EVZJ7NDV7BYIZZFUZ6.json","graph_json":"https://pith.science/api/pith-number/ZMOIRMT5EVZJ7NDV7BYIZZFUZ6/graph.json","events_json":"https://pith.science/api/pith-number/ZMOIRMT5EVZJ7NDV7BYIZZFUZ6/events.json","paper":"https://pith.science/paper/ZMOIRMT5"},"agent_actions":{"view_html":"https://pith.science/pith/ZMOIRMT5EVZJ7NDV7BYIZZFUZ6","download_json":"https://pith.science/pith/ZMOIRMT5EVZJ7NDV7BYIZZFUZ6.json","view_paper":"https://pith.science/paper/ZMOIRMT5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.00481&json=true","fetch_graph":"https://pith.science/api/pith-number/ZMOIRMT5EVZJ7NDV7BYIZZFUZ6/graph.json","fetch_events":"https://pith.science/api/pith-number/ZMOIRMT5EVZJ7NDV7BYIZZFUZ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZMOIRMT5EVZJ7NDV7BYIZZFUZ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZMOIRMT5EVZJ7NDV7BYIZZFUZ6/action/storage_attestation","attest_author":"https://pith.science/pith/ZMOIRMT5EVZJ7NDV7BYIZZFUZ6/action/author_attestation","sign_citation":"https://pith.science/pith/ZMOIRMT5EVZJ7NDV7BYIZZFUZ6/action/citation_signature","submit_replication":"https://pith.science/pith/ZMOIRMT5EVZJ7NDV7BYIZZFUZ6/action/replication_record"}},"created_at":"2026-07-02T01:17:44.617201+00:00","updated_at":"2026-07-02T01:17:44.617201+00:00"}