Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-01T02:00:13.598465Z
Paper Citation Record · LEDGER
As of 12 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 0 inbound Pith citation observations for arXiv:2607.25619.
A citation records a reference. It does not transfer a finding from one paper to another.
Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-01T02:00:13.598465Z
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links
A source-named dated measurement, never combined with another source.
Source: cited_works
38 of 38 outbound references displayed
External citation measurements
No source-named external measurement is stored.
Observation 6763f43c-1bbf-4fbc-b1c6-352bf4b942c4 · outbound
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents Clawhavoc poisons openclaw’s clawhub with 1,184 malicious skills,
Reference 1
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5a6ea652-8cd3-4c11-82e9-53389606877f · outbound
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents Vibe Coding vs. Agentic Coding: Fundamentals and Practical Implications of Agentic AI
Reference 2
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0f2c24a5-8336-4e29-9fa5-c8656748a570 · outbound
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents Usage, effects and requirements for ai coding assistants in the enterprise: An empirical study,
Reference 3
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a319f87f-95ff-4669-a065-e6c91a825b35 · outbound
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents Stack overflow developer survey 2024,
Reference 4
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6ac3eb18-4322-4cf5-ba63-0da34578dee3 · outbound
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents Swe-bench: Can language models resolve real-world github issues?
Reference 6
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 96a803b1-6073-4444-874d-438f96a56f3a · outbound
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents Model Context Protocol specification,
Reference 7
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e286e700-c207-4272-91ee-06193055ed11 · outbound
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents Backstabber’s knife collection: A review of open source software supply chain attacks,
Reference 8
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0084e253-9172-4e81-a4ab-1d1b7e8cf3bf · outbound
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents Small world with high risks: A study of security threats in the npm ecosystem,
Reference 9
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 21b61df0-05e4-462b-a513-83e58edb8be1 · outbound
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents Sok: Taxonomy of attacks on open-source software supply chains,
Reference 10
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b9c934c7-be9e-4e82-be16-3a9479d567ec · outbound
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents Semgrep: Static analysis at ludicrous speed,
Reference 11
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5a045591-1842-4d24-a50c-906e1ead14a2 · outbound
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents Snyk: Security platform for developers,
Reference 12
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2fb915f4-56ae-4dad-884d-5afb23e030c2 · outbound
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild
Reference 13
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a56964a0-d1ac-405f-b85e-01009b3ed6a0 · outbound
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks
Reference 14
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 88b9eb42-0e5d-4b59-b908-9b3a30087143 · outbound
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents MITRE ATT&CK: Adversarial tactics, techniques, and common knowledge,
Reference 15
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5a460739-1132-4275-adf9-ab6beac95ba6 · outbound
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents Sigma: Generic signature format for SIEM systems,
Reference 16
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 932a853f-faa3-4253-977a-e6d9488f8bbc · outbound
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents React: Synergizing reasoning and acting in language models,
Reference 17
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 594d3109-49d1-4ebf-b9dc-c485812e8cca · outbound
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents Toolformer: Language Models Can Teach Themselves to Use Tools
Reference 18
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a3a66830-0e38-4d3c-91b9-ab17ba37d3cd · outbound
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs
Reference 19
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 47e11240-ee1b-41ca-9180-e60e16fd4b14 · outbound
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents Asleep at the keyboard? assessing the security of github copilot’s code con- tributions,
Reference 20
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6ced6c73-4590-4ab5-917d-ef9e4cb6b737 · outbound
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents Do users write more insecure code with ai assistants?
Reference 21
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation df6d87ed-05b0-46b1-a165-48127f1e9623 · outbound
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents Practical automated detection of malicious npm packages,
Reference 22
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d374a5c3-461d-44c4-8232-2dbe742a5081 · outbound
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents SkillsBench-1650: A benchmark for AI agent skill safety detection,
Reference 23
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4911228b-9a5e-420a-b00c-81aeed75d70f · outbound
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents Not what you’ve signed up for: Compromising real-world llm-integrated applications with indirect prompt injection,
Reference 24
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 66223cfa-3042-4559-90f2-f144d6591917 · outbound
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents Open Source Security Foundation: Dependency review and SCA tooling,
Reference 25
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0107f286-2bd5-41dc-8504-249ee614077b · outbound
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents Ignore Previous Prompt: Attack Techniques For Language Models
Reference 26
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f39b4cd7-4535-4466-b430-dff46eb48631 · outbound
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents Formalizing and benchmarking prompt injection attacks and defenses,
Reference 27
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5b88294f-b252-436a-89c7-0ec1a19ad1a5 · outbound
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents Benchmarking and defending against indirect prompt injection attacks on large language models,
Reference 28
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 17beaf4f-1bf5-4402-b4d0-3e3b5a37f456 · outbound
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents Defending against indirect prompt injection attacks with spotlighting,
Reference 29
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 834fec72-69d6-4890-b663-31526e22f6b4 · outbound
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents Nemo guardrails: A toolkit for controllable and safe llm applications with programmable rails,
Reference 30
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b9ecdb16-2806-4f0a-a366-a493e158790e · outbound
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents Prompt injection and privilege separation in LLM applica- tions,
Reference 31
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1145033e-c602-4558-bc54-221d05f2b546 · outbound
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
Reference 32
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 113f8630-8195-48ed-a0d4-9337c3fc7fba · outbound
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents OpenAI moderation API,
Reference 33
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 884cac1e-ec43-4585-b341-618426f12e00 · outbound
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents ClawVet: Static analysis for MCP skill security,
Reference 34
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b3126426-85ef-4004-a4d1-b61bf432ed0f · outbound
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents skill-scanner: MCP skill security scanner,
Reference 35
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 780ef3cd-6349-4370-b678-88ebc32b6639 · outbound
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
Reference 36
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 747e01bf-88e0-4360-ac20-b0d6e89cd6a0 · outbound
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents The advantages of the matthews correlation coefficient (mcc) over f1 score and accuracy in binary classification evaluation,
Reference 37
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 505e73d5-31a7-4b63-bc08-57fa473957a3 · outbound
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents Evaluating Large Language Models Trained on Code
Reference 2021
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fe096eb2-f239-45ed-a84b-89f02b29ba84 · outbound
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents Toolformer: Language Models Can Teach Themselves to Use Tools
Reference 2023
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
No inbound Pith citation observations are available.