Skill 审计报告
ai-model-extraction 审计报告.
Extract or steal an ML/LLM model's parameters, training data, or system prompt via query access — model stealing, membership inference, training-data extraction. Load when testing an ML API/endpoint, "model extraction/inversion", data-leakage or IP-theft concerns, exposed inference endpoints. Signals: a predict/inference API, embeddings endpoint, fine-tuned model.
OpenAgentSkill 信任评分
OpenAgentSkill 信任评分
Trust Score 帮助 Agent 在安装前判断一个 Skill 是否足以进入候选清单。
GitHub 采用度
失败30
20 个 GitHub Stars
Star/Fork 活跃度
失败32
20 个 Star，7 个 Fork; 当前元数据中没有议题活跃度信息
近期维护
通过100
距上次推送 11 天
许可证清晰度
通过86
MIT
README/SKILL.md 完整度
信息76
公开元数据需要更完整的 README/SKILL.md 上下文
依赖与运行时风险
信息64
credential or environment access, network or browser surface
安装可用性
通过92
npx skills add NoorQureshi/SploitAgent --skill ai-model-extraction
安装命令安全性
通过92
标准软件包或运行时安装路径
权限范围
警告60
secrets or environment access, network or browser access
仓库证据
通过86
https://github.com/NoorQureshi/SploitAgent/tree/main/skills/ai-ml/ai-model-extraction
审查状态
警告46
缺少 AI 审查批准
Agent 验证结果
信息54
暂未有 Agent 结果数据
检查项
安装与采用审查
安装路径
92
npx skills add NoorQureshi/SploitAgent --skill ai-model-extraction
仓库
88
https://github.com/NoorQureshi/SploitAgent/tree/main/skills/ai-ml/ai-model-extraction
许可证
86
MIT
维护
100
距上次推送 11 天
AI 审查
55
Review approval is missing
README/SKILL.md 完整度
84
Usable description available
依赖风险
64
credential or environment access, network or browser surface
安装命令安全性
92
标准软件包或运行时安装路径
权限范围
60
secrets or environment access, network or browser access
Star/Fork 活跃度
32
20 个 Star，7 个 Fork; 当前元数据中没有议题活跃度信息
采用度
42
20 个 GitHub Stars
警告
- Permission surface may require sandboxing
- Low GitHub adoption signal
- 缺少 AI 审查批准
- Quality score needs review
- Permission surface needs review: secrets or environment access, network or browser access
- GitHub adoption: 20 GitHub stars
- Stars/forks activity: 20 stars, 7 forks; issue activity unavailable in current metadata
- Permission surface: secrets or environment access, network or browser access
- Review status: AI review approval is missing
方法
本报告综合公开元数据、AI 审查输出、仓库活跃度、安装就绪度、OpenAgentSkill 事件、质量评分、信任检查和 Agent 安全门槛；它不是完整的源代码安全审计。
对比相近选项
下一步可审计的相关 Skill
full-output-enforcement
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
96K Stars · 审计报告
distributed-llm-pretraining-torchtitan
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.
13K Stars · 审计报告
peft-fine-tuning
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
13K Stars · 审计报告