Skill-Audit-Bericht
weak-agent-test Audit-Bericht.
Run the weak-agent adversarial test harness against docx-cli. Spawns weak exercise agents (Haiku by default, Sonnet to probe, or a local agent harness's pre-produced runs) to perform real document tasks over six scenarios — five editing (MNDA form-fill + font fidelity, invoice table-edit/restructure + logo replace, résumé styling, contract redlining + commenting, contract finalize via accept/reject + comment reply/resolve) and one authoring (T. S. Eliot poetry journal: multi-column, verse, footnotes, links, figure) — renders every result with Word, has opus judge them against ground-truth rubrics, measures each exercise's tool economy, token cost, wall-clock, and correctness (from transcripts for Claude, the exercise.json ledger for the local harness), and synthesizes a prioritized ergonomics report. Use when the user says 'adversarial review', 'test docx-cli with weak agents', 'run the haiku harness', 'weak agent test', or wants to re-run yesterday's adversarial process.
OpenAgentSkill Trust Score
OpenAgentSkill Trust Score
The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.
GitHub-Akzeptanz
Info62
196 GitHub-Stars
Star-/Fork-Aktivität
Warnung51
196 Stars und 8 Forks; Issue-Aktivität ist in den aktuellen Metadaten nicht verfügbar
Aktuelle Wartung
Bestanden88
1 Monate seit dem letzten Push
Lizenzklarheit
Bestanden86
MIT
README/SKILL.md-Vollständigkeit
Bestanden86
Metadaten enthalten ausreichend Nutzungs- und Workflow-Kontext
Abhängigkeits-/Laufzeitrisiko
Warnung46
command execution surface, credential or environment access
Installationsverfügbarkeit
Bestanden92
npx skills add kklimuk/docx-cli --skill weak-agent-test
Sicherheit des Installationsbefehls
Bestanden92
Standard-Paket- oder Laufzeit-Installationspfad
Berechtigungsumfang
Fehlgeschlagen22
secrets or environment access, shell or command execution
Repository-Nachweis
Bestanden86
https://github.com/kklimuk/docx-cli/tree/main/.claude/skills/weak-agent-test
Prüfstatus
Info66
KI-Prüfdaten verfügbar
Agent-validierte Ergebnisse
Info54
Noch keine Agent-Ergebnisdaten
Prüfungen
Installations- und Adoptionsprüfung
Installationspfad
92
npx skills add kklimuk/docx-cli --skill weak-agent-test
Repository
88
https://github.com/kklimuk/docx-cli/tree/main/.claude/skills/weak-agent-test
Lizenz
86
MIT
Wartung
88
1 Monate seit dem letzten Push
KI-Prüfung
55
The skill is marked internal and is tightly coupled to the docx-cli repository; it may not be portable or meaningful outside that context.
README/SKILL.md-Vollständigkeit
86
Usable description available
Abhängigkeitsrisiko
46
command execution surface, credential or environment access
Sicherheit des Installationsbefehls
92
Standard-Paket- oder Laufzeit-Installationspfad
Berechtigungsumfang
22
secrets or environment access, shell or command execution
Star-/Fork-Aktivität
51
196 Stars und 8 Forks; Issue-Aktivität ist in den aktuellen Metadaten nicht verfügbar
Akzeptanz
68
196 GitHub-Stars
Financial decision safety
58
Research-only use: do not treat output as financial advice or execute a position without human approval.
Warnungen
- Dependency or permission surface needs review
- Permission surface may require sandboxing
- Financial research output is not financial advice; require human review before any live investment decision
- The skill is marked internal and is tightly coupled to the docx-cli repository; it may not be portable or meaningful outside that context.
- The SKILL.md references external scripts and workflows (e.g., .claude/workflows/weak-agent-test.js, scripts/stage-scenario.ts) that are not fully described within the skill itself, which could hinder understanding or reuse.
- Financial research output is not financial advice; require human review before any live investment decision.
- Quality score needs review
- Permission surface needs review: secrets or environment access, shell or command execution
- Stars/forks activity: 196 stars, 8 forks; issue activity unavailable in current metadata
- Dependency/runtime risk: command execution surface, credential or environment access
- Permission surface: secrets or environment access, shell or command execution
Methode
This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.
Nahe Optionen vergleichen
Ähnliche Skills als Nächstes prüfen
Code Review
Review a branch or diff against repository standards and the originating spec in two independent analysis passes.
169K Stars · Audit-Bericht
Appsmith
Platform to build admin panels, internal tools, and dashboards. Integrates with 25+ databases and any API.
41K Stars · Audit-Bericht
Implement
Implement work from an approved spec or ticket set, run focused and full tests, invoke code review, and commit the result to the current branch.
176K Stars · Audit-Bericht