← 返回 Skills 市场

Crypto News Noise Filter

Name: Crypto News Noise Filter
Author: harrylabsj

作者 haidong · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ⚠ suspicious

总下载

当前安装

版本数

在 OpenClaw 中安装

/install crypto-news-noise-filter

功能描述

A critical reading skill that helps users separate signal from hype in crypto news headlines. Use when the user sees alarming or exciting crypto news. Prompt...

使用说明 (SKILL.md)

crypto-news-noise-filter

A critical reading skill that helps users separate signal from hype in crypto news headlines.

Workflow

Take the news headline or pasted article text.
Identify what actually happened: separate facts from interpretation.
Check whether the headline matches the substance of the story.
Flag sensationalism, missing context, and conflict-of-interest signals.
Give a reading verdict: high signal, mixed, or noise.

Output Format

What actually happened
Headline vs. reality check
Context that changes the picture
Who benefits from this narrative
What to watch before reacting

Quality Bar

Does not declare the market direction or price impact.
Focuses on media quality and information integrity.
Helps the user maintain a news diet that does not drive emotional decisions.

Edge Cases

If the news involves a regulatory announcement, flag that interpretation is especially difficult and context matters enormously.
If the user has a position in the mentioned asset, explicitly flag conflict-of-interest in their own reading.

Compatibility

Prompt-only, no news API required.
Works from pasted text or manually described headlines.

安全使用建议

The skill's written instructions are benign (prompt-only), but the included handler.py contains a hard-coded file read from /Users/jianghaidong/.openclaw/skills/{skill_name}/SKILL.md — this is unnecessary for a headline-analysis skill and could expose local files. Before installing: (1) ask the publisher why the code reads that absolute path and request a version that does not access arbitrary home directories; (2) inspect or remove the file-read code (_load_skill_meta) or change it to read only packaged resources relative to the skill bundle; (3) run the skill in a sandboxed environment with no access to sensitive files or networks; (4) prefer skills from a known homepage/maintainer. If you cannot get a clear explanation or a fixed code version, avoid installing it.

功能分析

Type: OpenClaw Skill Name: crypto-news-noise-filter Version: 1.0.0 The skill contains a 'handler.py' file with a hardcoded absolute path referencing a specific local user directory (/Users/jianghaidong/), which is highly irregular for a portable skill bundle. Furthermore, the '_load_skill_meta' function uses the 'skill_name' argument to construct file paths without any sanitization, creating a Local File Inclusion (LFI) or path traversal vulnerability. While no explicit exfiltration logic is present, the combination of unsafe file handling and the discrepancy between the 'prompt-only' description in 'SKILL.md' and the actual Python implementation is a significant security risk.

能力标签

crypto

能力评估

⚠ Purpose & Capability

Name/description: crypto headline analysis. SKILL.md is prompt-only and needs no filesystem or credentials. However handler.py tries to load SKILL.md from a hard-coded absolute path (/Users/jianghaidong/.openclaw/skills/{skill_name}/SKILL.md). Reading an arbitrary user home path is unrelated to the stated purpose and is disproportionate.

ℹ Instruction Scope

The SKILL.md instructions are scoped to analyzing pasted headlines and explicitly say no API or external services are required. They do not mention reading local files or credentials. The handler implementation, however, instructs the runtime to read a specific local file path — a scope mismatch.

✓ Install Mechanism

No install spec (instruction-only) and no external downloads, so there is low install-time risk.

⚠ Credentials

No environment variables or credentials are declared or required by SKILL.md, yet the code accesses the local filesystem at a hard-coded user path. That access is not justified by the skill's purpose and could expose unrelated local data if the path or code is changed.

✓ Persistence & Privilege

always is false and the skill does not request system-wide changes or persistent privileges. It does not modify other skills' configs in the provided code.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install crypto-news-noise-filter
安装完成后，直接呼叫该 Skill 的名称或使用 /crypto-news-noise-filter 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

Initial release of crypto-news-noise-filter. - Enables critical reading of crypto news by separating facts from hype. - Flags sensationalism, missing context, and conflict-of-interest signals in headlines. - Provides a structured output: what happened, reality check, context, beneficiaries, and action tips. - Focuses on integrity of information, advising users against emotionally-driven decisions. - Designed for prompt-only use—no integrations or news APIs required.

元数据

Slug crypto-news-noise-filter

版本 1.0.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题