Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

Crypto News Noise Filter

v1.0.0

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...

0· 68·0 current·0 all-time
byhaidong@harrylabsj

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for harrylabsj/crypto-news-noise-filter.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Crypto News Noise Filter" (harrylabsj/crypto-news-noise-filter) from ClawHub.
Skill page: https://clawhub.ai/harrylabsj/crypto-news-noise-filter
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install crypto-news-noise-filter

ClawHub CLI

Package manager switcher

npx clawhub@latest install crypto-news-noise-filter
Security Scan
Capability signals
Crypto
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
VirusTotalVirusTotal
Suspicious
View report →
OpenClawOpenClaw
Suspicious
medium confidence
!
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.
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.
What to consider before installing
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.

Like a lobster shell, security has layers — review code before you run it.

latestvk975ha7p3f2q8fc4p2ybpdxyd584y5x6
68downloads
0stars
1versions
Updated 1w ago
v1.0.0
MIT-0

crypto-news-noise-filter

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

Workflow

  1. Take the news headline or pasted article text.
  2. Identify what actually happened: separate facts from interpretation.
  3. Check whether the headline matches the substance of the story.
  4. Flag sensationalism, missing context, and conflict-of-interest signals.
  5. 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.

Comments

Loading comments...