{"arxiv_id":"2608.17588","incoming":{"papers":0,"sentences":0,"groups":[],"unlabelled_sentences":0},"outgoing":{"papers":7,"sentences":19,"groups":[{"kind":"method_or_tool","label":"Uses the method or tool of","papers":1,"sentences":1,"quotes":[{"arxiv_id":"2605.18693","title":"SkillGenBench: Benchmarking Skill Generation Pipelines for LLM Agents","url":"/paper/2605.18693","section":"Runtime Execution Traces","sentence":"We follow the generation regimes introduced by SkillGenBench [ref] .","intent_p":1.0,"contests_p":null}]},{"kind":"data_used","label":"Uses data or values from","papers":4,"sentences":6,"quotes":[{"arxiv_id":"2605.18693","title":"SkillGenBench: Benchmarking Skill Generation Pipelines for LLM Agents","url":"/paper/2605.18693","section":"RQ3 Automated Skill Generation","sentence":"We conduct the experiment on all 187 samples in SkillGenBench [ref] and compare three conditions under the same benchmark tasks and evaluation procedure.","intent_p":0.89,"contests_p":null},{"arxiv_id":"2605.12015","title":"SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces","url":"/paper/2605.12015","section":"RQ2 Refinement Under Executable Attacks","sentence":"RQ2 evaluates the repaired Skills on all 155 cases from SkillSafetyBench [ref] .","intent_p":0.99,"contests_p":null},{"arxiv_id":"2602.20156","title":"Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks","url":"/paper/2602.20156","section":"RQ1 Safety Vulnerability Detection","sentence":"We use all 84 matched pairs from SkillInject [ref] .","intent_p":0.99,"contests_p":null},{"arxiv_id":"2601.10338","title":"Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale","url":"/paper/2601.10338","section":"Security of Agent Skills","sentence":"Large scale analysis has found that 26.1% of examined skills contain at least one vulnerability, with data exfiltration and privilege escalation among the most prevalent categories [ref] .","intent_p":0.95,"contests_p":null}]},{"kind":"supports_this_paper","label":"Cites as support","papers":1,"sentences":1,"quotes":[{"arxiv_id":"2601.10338","title":"Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale","url":"/paper/2601.10338","section":"Introduction","sentence":"Recent security studies have shown that unsafe skills can introduce serious vulnerabilities into LLM-based agents, exposing users and their local environments to substantial security risks [ref] .","intent_p":0.97,"contests_p":null}]}],"unlabelled_sentences":11},"claims":[],"thresholds":{"intent_p":0.8,"supports_p":0.95,"contests_p":0.7},"method":"Citing sentences come from each paper's LaTeX source; every \\cite marks the sentence and the works it cites. Pith's classifier typed each sentence. A label is shown at intent probability 0.8 or more (0.95 for support), a contest at 0.7 or more. Measured accuracy against two blind model families is at https://pith.science/accuracy. The quoted sentences are the citing authors' own.","held_up":null,"_links":{"html":"https://pith.science/paper/2608.17588"}}