ClawHub
Back to skill

Security audit

ClawHub Download Tracker

Security checks across malware telemetry and agentic risk

Overview

This skill coherently tracks ClawHub download counts, stores local history, and optionally sends configured Feishu notifications without evidence of hidden or unrelated behavior.

Install only if you want local download-history tracking and, if configured, Feishu messages containing skill slugs, notes, download counts, deltas, and report text. If you use Feishu, store the `.env` file carefully, restrict its permissions, and avoid putting sensitive notes in monitored skill entries.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (5)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The README describes Feishu push notifications and local storage behavior, but it does not clearly warn users that monitoring data and historical logs/reports are persisted locally and transmitted to a third-party messaging platform. This creates a transparency and privacy risk: users may enable the skill without understanding that skill identifiers, download metrics, notes, and reporting history are retained and sent externally.

Missing User Warnings

Medium
Confidence
68% confidence
Finding
The script automatically transmits report content and identifiers to Feishu without prominent runtime disclosure or explicit consent gating. In environments where users may not expect outbound messaging, this can lead to unintentional disclosure of monitored skill names, usage trends, and account identifiers to a third-party service.

Missing User Warnings

Low
Confidence
62% confidence
Finding
The code loads secrets from environment variables and a plaintext `.env` file without warning users about sensitive secret handling or recommended file protections. This increases the chance of accidental exposure through weak file permissions, backups, or unsafe operational practices.

Credential Access

High
Category
Privilege Escalation
Content
os.makedirs(DATA_DIR, exist_ok=True)
os.makedirs(REPORT_DIR, exist_ok=True)

# 从环境变量或 .env 文件读取飞书凭证（不硬编码）
_env_path = os.path.join(DATA_DIR, ".env")
if os.path.exists(_env_path):
    with open(_env_path) as _f:
Confidence
64% confidence
Finding
.env

Credential Access

High
Category
Privilege Escalation
Content
os.makedirs(REPORT_DIR, exist_ok=True)

# 从环境变量或 .env 文件读取飞书凭证（不硬编码）
_env_path = os.path.join(DATA_DIR, ".env")
if os.path.exists(_env_path):
    with open(_env_path) as _f:
        for _line in _f:
Confidence
64% confidence
Finding
.env"

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.