Skill-Audit-Bericht
ml4t-agent-tool-contracts Audit-Bericht.
Typed tool contracts for autonomous research agents. Use when exposing files, search, databases, or execution tools to an LLM agent.
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
Fehlgeschlagen30
23 GitHub-Stars
Star-/Fork-Aktivität
Fehlgeschlagen37
23 Stars und 12 Forks; Issue-Aktivität ist in den aktuellen Metadaten nicht verfügbar
Aktuelle Wartung
Bestanden100
2 Tage seit dem letzten Push
Lizenzklarheit
Bestanden86
Apache-2.0
README/SKILL.md-Vollständigkeit
Info76
Öffentliche Metadaten benötigen mehr README/SKILL.md-Kontext
Abhängigkeits-/Laufzeitrisiko
Warnung56
command execution surface, network or browser surface
Installationsverfügbarkeit
Bestanden92
npx skills add ml4t/skills --skill ml4t-agent-tool-contracts
Sicherheit des Installationsbefehls
Bestanden92
Standard-Paket- oder Laufzeit-Installationspfad
Berechtigungsumfang
Fehlgeschlagen36
shell or command execution, filesystem or document access
Repository-Nachweis
Bestanden86
https://github.com/ml4t/skills/tree/main/advanced-ai/agent-tool-contracts
Prüfstatus
Warnung46
KI-Prüffreigabe fehlt
Agent-validierte Ergebnisse
Info54
Noch keine Agent-Ergebnisdaten
Prüfungen
Installations- und Adoptionsprüfung
Installationspfad
92
npx skills add ml4t/skills --skill ml4t-agent-tool-contracts
Repository
88
https://github.com/ml4t/skills/tree/main/advanced-ai/agent-tool-contracts
Lizenz
86
Apache-2.0
Wartung
100
2 Tage seit dem letzten Push
KI-Prüfung
55
Review approval is missing
README/SKILL.md-Vollständigkeit
84
Usable description available
Abhängigkeitsrisiko
56
command execution surface, network or browser surface
Sicherheit des Installationsbefehls
92
Standard-Paket- oder Laufzeit-Installationspfad
Berechtigungsumfang
36
shell or command execution, filesystem or document access
Star-/Fork-Aktivität
37
23 Stars und 12 Forks; Issue-Aktivität ist in den aktuellen Metadaten nicht verfügbar
Akzeptanz
42
23 GitHub-Stars
Warnungen
- Dependency or permission surface needs review
- Permission surface may require sandboxing
- Low GitHub adoption signal
- KI-Prüffreigabe fehlt
- Quality score needs review
- Permission surface needs review: shell or command execution, filesystem or document access
- GitHub adoption: 23 GitHub stars
- Stars/forks activity: 23 stars, 12 forks; issue activity unavailable in current metadata
- Dependency/runtime risk: command execution surface, network or browser surface
- Permission surface: shell or command execution, filesystem or document access
- Review status: AI review approval is missing
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
litert-lm
Creates an Android app that runs an open text LLM on the device, on the CPU or the GPU, with the LiteRT-LM Kotlin API. Use this skill to build a new chat, summarization or extraction app with a .litertlm model from Hugging Face litert-community (Gemma, Qwen, Llama, Phi) - the dependency and manifest entries, getting the model file onto the device, engine initialization, a streamed multi-turn conversation, the ViewModel and screen.
459 Stars · Audit-Bericht
quark-torch-llm-ptq
Runs an end-to-end AMD Quark post-training quantization workflow for PyTorch / Hugging Face LLMs: inspect a Hub or local model, choose a quantization plan, create reproducible artifacts, request execution approval, and produce a quantized model. Applies to Llama, Qwen, Mistral, and similar transformer LLM requests involving FP8, INT4, or another Quark scheme. Does not handle .onnx model inputs or ONNX PTQ.
395 Stars · Audit-Bericht
lintlang
Lint AI agent instruction files (SKILL.md, CLAUDE.md, AGENTS.md, GEMINI.md), tool definitions, system prompts, and agent configs with the deterministic LintLang CLI. Use when writing, editing, or reviewing agent instructions to catch ambiguous tool descriptions, missing stop conditions, schema/description mismatches, mixed output formats, or prompts embedded in Python before they reach runtime. Zero-LLM static analysis; no model calls and no network calls during a scan.
137 Stars · Audit-Bericht