Skills/ClawHub/rag-optimization

rag-optimization@1.0.1

VERIFIED· install only

Publisher claims: "完整的RAG系统优化方案,涵盖21+种策略(Self-RAG、命题分块、上下文压缩、引用溯源、查询意图等);提供诊断工具、实现代码与评估框架;当用户需要优化知识库问答、提升检索准确率、降低幻觉或评估RAG效果时使用" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher kiwifruit13 · publishing for 95 daysInstalls 886Last detonated 3d ago
$clawhub install rag-optimization
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-07 and scored it 87/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathsscripts/evaluate.py:89 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# 说明:项目实际使用 NVIDIA API(通过 .env 桥接),豆包变量名保持不变Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsSKILL.md:318 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files**零配置加载**:`from llm_client import load_from_env; llm = load_from_env()` —— 自动读取环境变量(含 `.env` 文件)中的 API 凭证,配置方法见 [全局操作说明](references/global-operations.md)。Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/llm_client.py:48 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# 可选 .env 加载(H4:让 load_from_env() 名副其实)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/evaluate.py:61 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system fileslogger.debug(f".env 加载状态: {'已加载' if DOTENV_LOADED else '未加载(依赖真实环境变量)'}")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/evaluate.py:28 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# 自动加载 .envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/llm_client.py:22 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# 方式 2:从 .env 自动加载 NVIDIA 配置(零配置)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsSKILL.md:442 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- **环境准备**:参考 [全局操作说明](references/global-operations.md) 完成依赖安装和配置;LLM 凭证通过环境变量或项目根目录 `.env` 文件注入(格式模板见该文档 1.4 节),切勿将真实凭证写入任何被分发/提交的文件Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/evaluate.py:202 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filessource = "环境变量 NVIDIA_API_KEY (自动桥接,来自 .env)"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/evaluate.py:199 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# 方式 4:桥接 NVIDIA API 凭证(来自 .env 文件)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsSKILL.md:424 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files| [global-operations.md](references/global-operations.md) | 全局操作说明(环境准备、LLM 凭证配置、`.env` 格式、参数调优) |Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/llm_client.py:61 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files是否成功加载了 .envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/llm_client.py:52 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files尝试加载 .env 文件;python-dotenv 未安装时静默跳过。Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/llm_client.py:58 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files因此真实环境注入的凭证优先级高于 .env(符合直觉)。Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈3,164 tok
1 file · 37 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.