Skill flagged — suspicious patterns detected

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

Crypto Drawdown Journal

v1.0.0

A guided journal for processing a crypto loss or drawdown in a healthy, non-shaming way. Use when the user has experienced a loss and wants to reflect. Promp...

0· 57·0 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-drawdown-journal.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Crypto Drawdown Journal" (harrylabsj/crypto-drawdown-journal) from ClawHub.
Skill page: https://clawhub.ai/harrylabsj/crypto-drawdown-journal
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-drawdown-journal

ClawHub CLI

Package manager switcher

npx clawhub@latest install crypto-drawdown-journal
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
The skill is described as a prompt-only guided journal and requires no credentials or binaries, yet handler.py tries to read a local SKILL.md from a hard-coded absolute path (/Users/jianghaidong/.openclaw/skills/{skill_name}). Reading arbitrary local files is not necessary for a journaling prompt and is disproportionate to the stated purpose.
!
Instruction Scope
SKILL.md's runtime instructions are prompt-only and never mention reading the filesystem. The handler's runtime behavior (opening a SKILL.md from a specific home directory based on skill_name) goes beyond the documented instructions and could expose local file contents. The handler does no sanitization of skill_name, creating a risk of path-traversal reads.
Install Mechanism
There is no install spec (instruction-only style) and no external downloads. The risk comes from the included local code file, not from any installer or network fetch.
!
Credentials
No environment variables or credentials are requested, which is correct for the stated purpose — but the code's hard-coded path to /Users/jianghaidong/... is unexpected and suggests either leftover developer-specific code or a potential privacy leak. The filesystem access is not justified by the skill's description.
Persistence & Privilege
The skill is not marked always:true and does not request persistent platform-wide privileges. The handler does not modify agent configuration. The primary issue is local file reads rather than elevated persistence.
What to consider before installing
This skill appears to be a benign journaling prompt, but the included handler.py contains a hard-coded absolute path (/Users/jianghaidong/.openclaw/skills/{skill_name}) and will open files from the local filesystem based on the provided skill_name. That behavior is unnecessary for a journaling prompt and could be used to read sensitive local files (including via path-traversal if skill_name is attacker-controlled). Before installing or enabling this skill: - Ask the maintainer why the handler reads a local SKILL.md and why the path is hard-coded to another user's home directory. This may be a leftover developer artifact. - Request that the code be removed or modified so it does not access arbitrary filesystem locations (e.g., remove file reads, or restrict to packaged resources and sanitize input). - If you must run it, run in an isolated/sandboxed environment where it cannot access sensitive files. - Prefer the SKILL.md (prompt-only) behavior over executing the handler; if the platform allows, use the prompt-only implementation instead of executing included code. Given the mismatch between declared behavior and actual file access, treat this skill as suspicious until the filesystem-read behavior is explained or removed.

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

latestvk975ndeex96bzyhqyg05j7spsh84zy2q
57downloads
0stars
1versions
Updated 1w ago
v1.0.0
MIT-0

crypto-drawdown-journal

A guided journal for processing a crypto loss or drawdown in a healthy, non-shaming way.

Workflow

  1. Ask what happened: position, size, time horizon, and what the loss means in real life terms.
  2. Separate the outcome from the decision process: was the decision reasonable given what was known?
  3. Identify what was in the user's control versus what was not.
  4. Surface emotional reactions and name them without judgment.
  5. Extract 1-2 practical lessons without spiraling into self-punishment.

Output Format

  • What happened (facts)
  • What was the decision at the time
  • What went well and what went off-plan
  • Emotional check-in
  • One practical lesson to carry forward
  • One self-care note

Quality Bar

  • Non-judgmental and compassionate.
  • Converts emotional pain into useful information.
  • Does not allow the spiral of "I should have known" when the information was genuinely unavailable.

Edge Cases

  • If the loss is severe enough to affect daily life, recommend professional support, not just journaling.
  • If the user shows signs of compulsive trading patterns, flag this gently and recommend stepping back.

Compatibility

  • Prompt-only, works from memory and rough notes.
  • Best used alone or with a trusted person, not as a trading journal.

Comments

Loading comments...