{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DACRINKV3S76IOEOCRJU5CIEVO","short_pith_number":"pith:DACRINKV","schema_version":"1.0","canonical_sha256":"1805143555dcbfe4388e14534e8904ab886bd8d377b3555077b02869c62f9ffa","source":{"kind":"arxiv","id":"2506.17266","version":1},"attestation_state":"computed","paper":{"title":"Securing Generative AI Agentic Workflows: Risks, Mitigation, and a Proposed Firewall Architecture","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Gopala Dhar, Sunil Kumar Jang Bahadur","submitted_at":"2025-06-10T07:36:54Z","abstract_excerpt":"Generative Artificial Intelligence (GenAI) presents significant advancements but also introduces novel security challenges, particularly within agentic workflows where AI agents operate autonomously. These risks escalate in multi-agent systems due to increased interaction complexity. This paper outlines critical security vulnerabilities inherent in GenAI agentic workflows, including data privacy breaches, model manipulation, and issues related to agent autonomy and system integration. It discusses key mitigation strategies such as data encryption, access control, prompt engineering, model moni"},"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":"2506.17266","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-06-10T07:36:54Z","cross_cats_sorted":[],"title_canon_sha256":"5d47df4bff63f449cc1f5643d4f0eac02a1a17fd87fdefb164ee310dd2f83b13","abstract_canon_sha256":"d73f05bbefed7397a45756028852828792764d890e11fc3cd35b9ff906c0b5ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:14.499904Z","signature_b64":"ICOzyR8SL/sDT5yMnQ5I2tCyQqmIC5zd1KDqHStQHtvCyiVymLCYEE2rHobq/3GIFDm7U+0+svlslzKoDbmOAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1805143555dcbfe4388e14534e8904ab886bd8d377b3555077b02869c62f9ffa","last_reissued_at":"2026-07-05T11:25:14.499446Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:14.499446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Securing Generative AI Agentic Workflows: Risks, Mitigation, and a Proposed Firewall Architecture","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Gopala Dhar, Sunil Kumar Jang Bahadur","submitted_at":"2025-06-10T07:36:54Z","abstract_excerpt":"Generative Artificial Intelligence (GenAI) presents significant advancements but also introduces novel security challenges, particularly within agentic workflows where AI agents operate autonomously. These risks escalate in multi-agent systems due to increased interaction complexity. This paper outlines critical security vulnerabilities inherent in GenAI agentic workflows, including data privacy breaches, model manipulation, and issues related to agent autonomy and system integration. It discusses key mitigation strategies such as data encryption, access control, prompt engineering, model moni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17266","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/2506.17266/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":"2506.17266","created_at":"2026-07-05T11:25:14.499501+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.17266v1","created_at":"2026-07-05T11:25:14.499501+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17266","created_at":"2026-07-05T11:25:14.499501+00:00"},{"alias_kind":"pith_short_12","alias_value":"DACRINKV3S76","created_at":"2026-07-05T11:25:14.499501+00:00"},{"alias_kind":"pith_short_16","alias_value":"DACRINKV3S76IOEO","created_at":"2026-07-05T11:25:14.499501+00:00"},{"alias_kind":"pith_short_8","alias_value":"DACRINKV","created_at":"2026-07-05T11:25:14.499501+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10749","citing_title":"Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2603.09002","citing_title":"Security Considerations for Multi-agent Systems","ref_index":191,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DACRINKV3S76IOEOCRJU5CIEVO","json":"https://pith.science/pith/DACRINKV3S76IOEOCRJU5CIEVO.json","graph_json":"https://pith.science/api/pith-number/DACRINKV3S76IOEOCRJU5CIEVO/graph.json","events_json":"https://pith.science/api/pith-number/DACRINKV3S76IOEOCRJU5CIEVO/events.json","paper":"https://pith.science/paper/DACRINKV"},"agent_actions":{"view_html":"https://pith.science/pith/DACRINKV3S76IOEOCRJU5CIEVO","download_json":"https://pith.science/pith/DACRINKV3S76IOEOCRJU5CIEVO.json","view_paper":"https://pith.science/paper/DACRINKV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.17266&json=true","fetch_graph":"https://pith.science/api/pith-number/DACRINKV3S76IOEOCRJU5CIEVO/graph.json","fetch_events":"https://pith.science/api/pith-number/DACRINKV3S76IOEOCRJU5CIEVO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DACRINKV3S76IOEOCRJU5CIEVO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DACRINKV3S76IOEOCRJU5CIEVO/action/storage_attestation","attest_author":"https://pith.science/pith/DACRINKV3S76IOEOCRJU5CIEVO/action/author_attestation","sign_citation":"https://pith.science/pith/DACRINKV3S76IOEOCRJU5CIEVO/action/citation_signature","submit_replication":"https://pith.science/pith/DACRINKV3S76IOEOCRJU5CIEVO/action/replication_record"}},"created_at":"2026-07-05T11:25:14.499501+00:00","updated_at":"2026-07-05T11:25:14.499501+00:00"}