{"id":"cmuxhrnd40675ad07bceytubc","slug":"huggingface-tokenizers","publicId":"42ea50ea-f468-4273-9924-2ba4fcaa3eb2","name":"huggingface-tokenizers","description":"Fast BPE/WordPiece tokenization and custom vocab training.","version":"1.0.0","author":"Orchestra Research","license":"MIT","compatibility":"","status":"completed","overallGrade":"B","scannerVersion":11,"fileCount":5,"hasSkillMd":true,"hasScripts":false,"hasReferences":true,"hasEvals":false,"hasAssets":false,"sourceType":"github","sourceUrl":"https://github.com/NousResearch/hermes-agent/tree/main/optional-skills/mlops/huggingface-tokenizers","createdAt":"2026-10-07T02:31:47.463Z","completedAt":"2026-10-07T02:31:47.462Z","visibility":"public","publishedAt":"2026-07-28T15:35:27.239Z","category":"","frameworks":[],"badgeStatus":"conditional","downloadCount":0,"verdictRationale":{"summary":"Skill has warnings: 2 warnings in security or structure checks.","verdict":"warn","scanners":[{"source":"vettd","weight":1,"verdict":"warn"},{"source":"cisco","weight":0.8,"verdict":"pass"}],"consensus":"warn","warnTriggers":["Embedded chat-template special token","References external URL — review for indirect prompt injection risk"],"policyVersion":"consensus-v1","hardFailTriggers":[]},"verdictPolicyVersion":"consensus-v1","skillId":"cms4thypi0190ad06vvp1j03i","findings":[{"id":"cmuxhrnd40676ad07ak51vfs9","source":"vettd","category":"security","label":"Embedded chat-template special token","detail":"Detected in references/pipeline.md:359 — `**gpt-2 style** (`sentence <|endoftext|>`):`","severity":"medium","ruleId":"VTD-0076","owaspLlmCategory":null,"intent":null,"chainId":null,"fingerprint":"6d7b26a492cbacf27a9dcc36e3311715","filepath":"references/pipeline.md"},{"id":"cmuxhrnd40677ad07l8wm6xox","source":"vettd","category":"security","label":"References external URL — review for indirect prompt injection risk","detail":"External URL(s) detected in SKILL.md — referenced content can change after audit","severity":"medium","ruleId":"VTD-0088","owaspLlmCategory":null,"intent":null,"chainId":null,"fingerprint":"42638a8b7e9fc5df27449992eaebc724","filepath":"SKILL.md"}],"scannerRuns":[{"source":"cisco","status":"success","verdict":null,"grade":"A","findingCount":0,"criticalCount":0,"highCount":0},{"source":"vettd","status":"success","verdict":null,"grade":"B","findingCount":2,"criticalCount":0,"highCount":0}],"user":{"name":"Justin Pacella","image":"https://avatars.githubusercontent.com/u/97124458?v=4"},"repository":{"owner":"NousResearch","name":"hermes-agent"},"freshness":{"status":"verified_unchanged","reason":null,"retryable":false,"renamedTo":null,"lastCheckedAt":"2026-10-21T11:16:39.326Z","lastVerifiedAt":"2026-10-21T11:16:39.326Z","lastChangeDetectedAt":"2026-08-14T10:43:28.360Z","scannedHash":"ec8bdc90ab47d5f0b5c01e946df0d5b5b2ed3983","latestUpstreamHash":"ec8bdc90ab47d5f0b5c01e946df0d5b5b2ed3983","nextCheckDueAt":"2026-10-22T13:19:42.381Z"},"signalCategories":[{"category":"safety","label":"Safety","form":"graded","verdict":null,"rows":[]},{"category":"reliability","label":"Reliability & Quality","form":"graded","verdict":null,"rows":[]},{"category":"performance","label":"Performance","form":"measured","verdict":{"form":"measured","magnitudes":[{"ruleId":"performance/static-context-tokens","label":"Static context tokens","value":3340,"unit":null,"method":"tiktoken/cl100k_base/skill-md-body"}]},"rows":[{"origin":"signal","id":"cmuxhrowt06evad07xoy6a4eh","subjectType":"skill_audit","subjectId":"cmuxhrnd40675ad07bceytubc","relatedType":"","relatedId":"","dataCategory":"performance","sourceClass":"scan","source":"vettd","ruleId":"performance/progressive-disclosure","severity":null,"label":"Progressive disclosure","detail":null,"valueNum":null,"valueText":"present","unit":null,"method":null,"derivation":"read","confidence":null,"sampleSize":null,"synthetic":false,"firstParty":true,"observedAt":"2026-10-07T02:31:44.000Z","payload":null},{"origin":"signal","id":"cmuxhrnr8068fad07x54bxtmk","subjectType":"skill_audit","subjectId":"cmuxhrnd40675ad07bceytubc","relatedType":"","relatedId":"","dataCategory":"performance","sourceClass":"scan","source":"vettd","ruleId":"performance/static-context-tokens","severity":null,"label":"Static context tokens","detail":null,"valueNum":3340,"valueText":null,"unit":null,"method":"tiktoken/cl100k_base/skill-md-body","derivation":null,"confidence":null,"sampleSize":null,"synthetic":false,"firstParty":true,"observedAt":"2026-10-07T02:31:44.000Z","payload":null}]},{"category":"cost","label":"Cost","form":"measured","verdict":null,"rows":[]},{"category":"compatibility","label":"Compatibility","form":"unjudged","verdict":{"form":"unjudged"},"rows":[{"origin":"signal","id":"cmuxhrntl068oad07fryeypnl","subjectType":"skill_audit","subjectId":"cmuxhrnd40675ad07bceytubc","relatedType":"","relatedId":"","dataCategory":"compatibility","sourceClass":"scan","source":"vettd","ruleId":"compatibility/declared-environment-assumptions","severity":null,"label":"Declared environment assumptions","detail":null,"valueNum":null,"valueText":"","unit":null,"method":null,"derivation":"read","confidence":null,"sampleSize":null,"synthetic":false,"firstParty":true,"observedAt":"2026-10-07T02:31:44.000Z","payload":null},{"origin":"signal","id":"cmuxhrog306amad07orpfdh11","subjectType":"skill_audit","subjectId":"cmuxhrnd40675ad07bceytubc","relatedType":"","relatedId":"","dataCategory":"compatibility","sourceClass":"scan","source":"vettd","ruleId":"compatibility/declared-name","severity":null,"label":"Declared skill name","detail":null,"valueNum":null,"valueText":"huggingface-tokenizers","unit":null,"method":null,"derivation":"read","confidence":null,"sampleSize":null,"synthetic":false,"firstParty":true,"observedAt":"2026-10-07T02:31:44.000Z","payload":null}]},{"category":"sentiment","label":"Popularity","form":"unjudged","verdict":null,"rows":[]},{"category":"characteristics","label":"Characteristics","form":"unjudged","verdict":null,"rows":[]}],"signalCount":25,"publisherSupplied":["name","description","author","version","license"]}