{"id":"cmuxjxp0o1di4ad07yyr6053t","slug":"agent-eval","publicId":"cfd4299d-6245-40ec-93b1-caa781f3508f","name":"agent-eval","description":"编码代理（Claude Code、Aider、Codex等）在自定义任务上的直接比较，包含通过率、成本、时间和一致性指标","version":"","author":"affaan-m","license":"MIT","compatibility":"","status":"completed","overallGrade":"B","scannerVersion":11,"fileCount":1,"hasSkillMd":true,"hasScripts":false,"hasReferences":false,"hasEvals":false,"hasAssets":false,"sourceType":"github","sourceUrl":"https://github.com/affaan-m/ecc/tree/main/docs/zh-CN/skills/agent-eval","createdAt":"2026-10-07T03:32:28.472Z","completedAt":"2026-10-07T03:32:28.470Z","visibility":"public","publishedAt":"2026-08-06T17:11:19.022Z","category":"","frameworks":[],"badgeStatus":"conditional","downloadCount":0,"verdictRationale":{"summary":"Skill has warnings: 1 warning in security or structure checks.","verdict":"warn","scanners":[{"source":"vettd","weight":1,"verdict":"warn"},{"source":"cisco","weight":0.8,"verdict":"pass"}],"consensus":"warn","warnTriggers":["References external URL — review for indirect prompt injection risk"],"policyVersion":"consensus-v1","hardFailTriggers":[]},"verdictPolicyVersion":"consensus-v1","skillId":"cmshrvwtl04fzad07fpv1u2pb","findings":[{"id":"cmuxjxp0o1di5ad07ewx67kia","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"},{"id":"cmuxjxp0o1di6ad074rn2l8cu","source":"cisco","category":"security","label":"Skill does not specify a license","detail":"SKILL.md — Skill manifest does not include a 'license' field. Specifying a license helps users understand usage terms.","severity":"info","ruleId":"MANIFEST_MISSING_LICENSE","owaspLlmCategory":null,"intent":null,"chainId":null,"fingerprint":"592f7ac7731768f0fd0bba83f30850f9","filepath":"SKILL.md"}],"scannerRuns":[{"source":"cisco","status":"success","verdict":null,"grade":"A","findingCount":1,"criticalCount":0,"highCount":0},{"source":"vettd","status":"success","verdict":null,"grade":"B","findingCount":1,"criticalCount":0,"highCount":0}],"user":{"name":"Justin Pacella","image":"https://avatars.githubusercontent.com/u/97124458?v=4"},"repository":{"owner":"affaan-m","name":"ecc"},"freshness":{"status":"verified_unchanged","reason":null,"retryable":false,"renamedTo":null,"lastCheckedAt":"2026-10-21T18:26:41.286Z","lastVerifiedAt":"2026-10-21T18:26:41.286Z","lastChangeDetectedAt":"2026-08-14T15:33:28.694Z","scannedHash":"adc47bd9d9834a1f46a756e74faa9a49294f1f9d","latestUpstreamHash":"adc47bd9d9834a1f46a756e74faa9a49294f1f9d","nextCheckDueAt":"2026-10-22T19:38:21.254Z"},"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":1364,"unit":null,"method":"tiktoken/cl100k_base/skill-md-body"}]},"rows":[{"origin":"signal","id":"cmuxjxwqf1eo6ad076521pnsd","subjectType":"skill_audit","subjectId":"cmuxjxp0o1di4ad07yyr6053t","relatedType":"","relatedId":"","dataCategory":"performance","sourceClass":"scan","source":"vettd","ruleId":"performance/progressive-disclosure","severity":null,"label":"Progressive disclosure","detail":null,"valueNum":null,"valueText":"absent","unit":null,"method":null,"derivation":"read","confidence":null,"sampleSize":null,"synthetic":false,"firstParty":true,"observedAt":"2026-10-07T03:32:23.000Z","payload":null},{"origin":"signal","id":"cmuxjxps11do2ad071c1ak2y1","subjectType":"skill_audit","subjectId":"cmuxjxp0o1di4ad07yyr6053t","relatedType":"","relatedId":"","dataCategory":"performance","sourceClass":"scan","source":"vettd","ruleId":"performance/static-context-tokens","severity":null,"label":"Static context tokens","detail":null,"valueNum":1364,"valueText":null,"unit":null,"method":"tiktoken/cl100k_base/skill-md-body","derivation":null,"confidence":null,"sampleSize":null,"synthetic":false,"firstParty":true,"observedAt":"2026-10-07T03:32:23.000Z","payload":null}]},{"category":"cost","label":"Cost","form":"measured","verdict":null,"rows":[]},{"category":"compatibility","label":"Compatibility","form":"unjudged","verdict":{"form":"unjudged"},"rows":[{"origin":"signal","id":"cmuxjxqp61dprad07q0ss5oi3","subjectType":"skill_audit","subjectId":"cmuxjxp0o1di4ad07yyr6053t","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":"2026-10-07T03:32:23.000Z","payload":null},{"origin":"signal","id":"cmuxjxucd1e80ad07ot6b1riz","subjectType":"skill_audit","subjectId":"cmuxjxp0o1di4ad07yyr6053t","relatedType":"","relatedId":"","dataCategory":"compatibility","sourceClass":"scan","source":"vettd","ruleId":"compatibility/declared-name","severity":null,"label":"Declared skill name","detail":null,"valueNum":null,"valueText":"agent-eval","unit":null,"method":null,"derivation":"read","confidence":null,"sampleSize":null,"synthetic":false,"firstParty":true,"observedAt":"2026-10-07T03:32:23.000Z","payload":null},{"origin":"signal","id":"cmuxjxshi1du2ad0707ri718n","subjectType":"skill_audit","subjectId":"cmuxjxp0o1di4ad07yyr6053t","relatedType":"declared_tool","relatedId":"Bash","dataCategory":"compatibility","sourceClass":"scan","source":"vettd","ruleId":"compatibility/declared-required-tools","severity":null,"label":"Declared required tool","detail":null,"valueNum":null,"valueText":"Bash","unit":null,"method":null,"derivation":"read","confidence":null,"sampleSize":null,"synthetic":false,"firstParty":true,"observedAt":"2026-10-07T03:32:23.000Z","payload":null},{"origin":"signal","id":"cmuxjxspo1dvhad07w6rrwl69","subjectType":"skill_audit","subjectId":"cmuxjxp0o1di4ad07yyr6053t","relatedType":"declared_tool","relatedId":"Edit","dataCategory":"compatibility","sourceClass":"scan","source":"vettd","ruleId":"compatibility/declared-required-tools","severity":null,"label":"Declared required tool","detail":null,"valueNum":null,"valueText":"Edit","unit":null,"method":null,"derivation":"read","confidence":null,"sampleSize":null,"synthetic":false,"firstParty":true,"observedAt":"2026-10-07T03:32:23.000Z","payload":null},{"origin":"signal","id":"cmuxjxsvl1dwrad07ap72tqfy","subjectType":"skill_audit","subjectId":"cmuxjxp0o1di4ad07yyr6053t","relatedType":"declared_tool","relatedId":"Glob","dataCategory":"compatibility","sourceClass":"scan","source":"vettd","ruleId":"compatibility/declared-required-tools","severity":null,"label":"Declared required tool","detail":null,"valueNum":null,"valueText":"Glob","unit":null,"method":null,"derivation":"read","confidence":null,"sampleSize":null,"synthetic":false,"firstParty":true,"observedAt":"2026-10-07T03:32:23.000Z","payload":null},{"origin":"signal","id":"cmuxjxt3s1dy2ad070uyh4t2b","subjectType":"skill_audit","subjectId":"cmuxjxp0o1di4ad07yyr6053t","relatedType":"declared_tool","relatedId":"Grep","dataCategory":"compatibility","sourceClass":"scan","source":"vettd","ruleId":"compatibility/declared-required-tools","severity":null,"label":"Declared required tool","detail":null,"valueNum":null,"valueText":"Grep","unit":null,"method":null,"derivation":"read","confidence":null,"sampleSize":null,"synthetic":false,"firstParty":true,"observedAt":"2026-10-07T03:32:23.000Z","payload":null},{"origin":"signal","id":"cmuxjxtbr1dzvad076hfaujts","subjectType":"skill_audit","subjectId":"cmuxjxp0o1di4ad07yyr6053t","relatedType":"declared_tool","relatedId":"Read","dataCategory":"compatibility","sourceClass":"scan","source":"vettd","ruleId":"compatibility/declared-required-tools","severity":null,"label":"Declared required tool","detail":null,"valueNum":null,"valueText":"Read","unit":null,"method":null,"derivation":"read","confidence":null,"sampleSize":null,"synthetic":false,"firstParty":true,"observedAt":"2026-10-07T03:32:23.000Z","payload":null},{"origin":"signal","id":"cmuxjxtkb1e1sad079sm17e4l","subjectType":"skill_audit","subjectId":"cmuxjxp0o1di4ad07yyr6053t","relatedType":"declared_tool","relatedId":"Write","dataCategory":"compatibility","sourceClass":"scan","source":"vettd","ruleId":"compatibility/declared-required-tools","severity":null,"label":"Declared required tool","detail":null,"valueNum":null,"valueText":"Write","unit":null,"method":null,"derivation":"read","confidence":null,"sampleSize":null,"synthetic":false,"firstParty":true,"observedAt":"2026-10-07T03:32:23.000Z","payload":null}]},{"category":"sentiment","label":"Popularity","form":"unjudged","verdict":null,"rows":[]},{"category":"characteristics","label":"Characteristics","form":"unjudged","verdict":null,"rows":[]}],"signalCount":31,"publisherSupplied":["name","description","author","version","license"]}