{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QNAIEZPXGTUXRAJ2PJJ5P7LS6J","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"cbc7f6a4187d1355bd35f6550cf41d65ca107a9fa6e326b9596d8499773fa324","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2026-06-16T18:04:45Z","title_canon_sha256":"f2a4bd9d5f8825313ea4300f55b757c57e2751c0db0ca62b75a5e2d37bf056ca"},"schema_version":"1.0","source":{"id":"2606.18356","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.18356","created_at":"2026-06-19T16:10:58Z"},{"alias_kind":"arxiv_version","alias_value":"2606.18356v1","created_at":"2026-06-19T16:10:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18356","created_at":"2026-06-19T16:10:58Z"},{"alias_kind":"pith_short_12","alias_value":"QNAIEZPXGTUX","created_at":"2026-06-19T16:10:58Z"},{"alias_kind":"pith_short_16","alias_value":"QNAIEZPXGTUXRAJ2","created_at":"2026-06-19T16:10:58Z"},{"alias_kind":"pith_short_8","alias_value":"QNAIEZPX","created_at":"2026-06-19T16:10:58Z"}],"graph_snapshots":[{"event_id":"sha256:a4850817877f2db676198f4877237e014f365bcfff4353c09160e10f9db4f372","target":"graph","created_at":"2026-06-19T16:10:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.18356/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tool-using language-model agents introduce security failures that go beyond unsafe text: they can disclose protected objects, write persistent memory, send messages, modify databases, or trigger harmful code and tool effects. Existing evaluations often collapse these stages into a single attack success rate, making it difficult to tell whether a model merely agreed with an attacker or actually produced observable harm. We introduce SafeClawBench, a staged benchmark for tool-using agent security with 600 controlled adversarial tasks across six attack families: direct and indirect prompt injecti","authors_text":"Chao Xu, Hanting Chen, Haocheng Mei, Mengyu Zheng, Xinghao Chen, Ye Yuan, Yuchuan Tian, Yu Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2026-06-16T18:04:45Z","title":"SafeClawBench: Separating Semantic, Audit-Evidence, and Sandbox Harm in Tool-Using LLM Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18356","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:dfbf9c45d0d46a230d1802559bf65bc5f2a5d0a3adcc3659085501aefc9dd93e","target":"record","created_at":"2026-06-19T16:10:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"cbc7f6a4187d1355bd35f6550cf41d65ca107a9fa6e326b9596d8499773fa324","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2026-06-16T18:04:45Z","title_canon_sha256":"f2a4bd9d5f8825313ea4300f55b757c57e2751c0db0ca62b75a5e2d37bf056ca"},"schema_version":"1.0","source":{"id":"2606.18356","kind":"arxiv","version":1}},"canonical_sha256":"83408265f734e978813a7a53d7fd72f26aaeff80d32416fec7b16a04206618ea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83408265f734e978813a7a53d7fd72f26aaeff80d32416fec7b16a04206618ea","first_computed_at":"2026-06-19T16:10:58.973294Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:10:58.973294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h5EIg5NIbgeSQfg0h94X4mRXG3sQ/I5njvRribadAnsQnJ+BaBwqe3mwKviGWrRyQe7bjvKeUM+iONwkelctDw==","signature_status":"signed_v1","signed_at":"2026-06-19T16:10:58.973813Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.18356","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dfbf9c45d0d46a230d1802559bf65bc5f2a5d0a3adcc3659085501aefc9dd93e","sha256:a4850817877f2db676198f4877237e014f365bcfff4353c09160e10f9db4f372"],"state_sha256":"d8df1ab692e1dfb95d17d5473bd5b2443740e45e295737c16da497ae2f09269d"}