ClawHub
Back to skill

Security audit

miao-vision

Security checks across malware telemetry and agentic risk

Overview

The skill mostly matches its visualization purpose, but it should be reviewed because it can fetch remote release content and permanently install itself into an agent skills directory without integrity checks.

Install only if you trust the publisher and the npm/GitHub release chain. Review the install commands before running them, prefer pinned versions with checksums or signatures, and avoid using the skill on sensitive private files or URLs unless you are comfortable with local CLI processing and temporary artifact storage.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Vague Triggers

Medium
Confidence
83% confidence
Finding
The trigger condition is very broad: phrases like 'turn this into an infographic' can match many ordinary requests and may cause this skill to activate in situations the user did not intend. Over-broad activation can route unrelated content into a workflow that fetches URLs, reads local files, and generates artifacts, increasing the chance of unintended data processing or surprising tool use.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger list is intentionally expansive and includes vague phrases like "for a meeting," "for executives," and "to present," which can cause this workflow to activate for requests that are only loosely related to deck generation. In an agent setting, over-broad routing can lead to unintended file processing, unnecessary command execution, and the wrong tool being used on sensitive or irrelevant inputs.

External Transmission

Medium
Category
Data Exfiltration
Content
# 2. Install the skill
SKILL_VERSION=$(npm show @miao-vision/cli version)
mkdir -p ~/.claude/skills
curl -fsSL "https://github.com/miaoshou-dev/miao-vision/releases/download/skill-v${SKILL_VERSION}/miao-vision-skill.zip" \
  -o /tmp/miao-vision-skill.zip
unzip -o /tmp/miao-vision-skill.zip -d ~/.claude/skills/
rm /tmp/miao-vision-skill.zip
Confidence
89% confidence
Finding
curl -fsSL "https://github.com/miaoshou-dev/miao-vision/releases/download/skill-v${SKILL_VERSION}/miao-vision-skill.zip" \ -o /tmp/miao-vision-skill.zip unzip -o /tmp/miao-vision-skill.zip -d

Session Persistence

Medium
Category
Rogue Agent
Content
# 2. Install the skill
SKILL_VERSION=$(npm show @miao-vision/cli version)
mkdir -p ~/.claude/skills
curl -fsSL "https://github.com/miaoshou-dev/miao-vision/releases/download/skill-v${SKILL_VERSION}/miao-vision-skill.zip" \
  -o /tmp/miao-vision-skill.zip
unzip -o /tmp/miao-vision-skill.zip -d ~/.claude/skills/
Confidence
86% confidence
Finding
mkdir -p ~/.claude/skills curl -fsSL "https://github.com/miaoshou-dev/miao-vision/releases/download/skill-v${SKILL_VERSION}/miao-vision-skill.zip" \ -o /tmp/miao-vision-skill.zip unzip -o /tmp/miao-

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.