ClawHub

AI Humanizer CN - 中文 AI 文本拟人优化

Security checks across malware telemetry and agentic risk

Overview

This text-rewriting skill may be useful, but users should review it because its files conflict about whether text stays local or is sent to third-party AI providers.

Install only if you are comfortable with the unresolved privacy ambiguity. Avoid confidential, regulated, or proprietary text unless you intentionally want it processed by the configured AI provider; keep batch paths narrow; use restricted API keys; and inspect any PyPI or GitHub version separately before installing it.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (9)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill explicitly requires third-party API keys and describes sending user content to external AI providers, but it does not clearly warn that input data may leave the local environment. This creates a real privacy and compliance risk, especially if users process sensitive documents, source code, or proprietary text under the assumption that processing is local.

Missing User Warnings

Medium
Confidence
86% confidence
Finding
The batch-processing examples show writing transformed outputs to files and directories without warning about overwrite behavior, destructive modification, or safe output handling. In practice this can lead to accidental loss or corruption of user files, especially when recursively processing folders or reusing output paths.

Natural-Language Policy Violations

Medium
Confidence
91% confidence
Finding
The method automatically invokes language detection on arbitrary input when the caller does not explicitly provide a language. In an AI text-processing skill, this can violate user expectations and data-minimization requirements because it performs additional inference on user content without explicit opt-in, which may be sensitive in privacy-conscious or regulated deployments.

Unpinned Dependencies

Low
Category
Supply Chain
Content
# Core dependencies
requests>=2.28.0
numpy>=1.20.0
pyyaml>=6.0
Confidence
93% confidence
Finding
requests>=2.28.0

Unpinned Dependencies

Low
Category
Supply Chain
Content
# Core dependencies
requests>=2.28.0
numpy>=1.20.0
pyyaml>=6.0

# Optional dependencies
Confidence
93% confidence
Finding
numpy>=1.20.0

Unpinned Dependencies

Low
Category
Supply Chain
Content
# Core dependencies
requests>=2.28.0
numpy>=1.20.0
pyyaml>=6.0

# Optional dependencies
# beautifulsoup4>=4.11.0  # HTML parsing
Confidence
94% confidence
Finding
pyyaml>=6.0

Known Vulnerable Dependency: requests — 10 advisory(ies): CVE-2014-1830 (Exposure of Sensitive Information to an Unauthorized Actor in Requests); CVE-2024-47081 (Requests vulnerable to .netrc credentials leak via malicious URLs); CVE-2024-35195 (Requests `Session` object does not verify requests after making first request wi) +7 more

High
Category
Supply Chain
Confidence
84% confidence
Finding
requests

Known Vulnerable Dependency: numpy — 10 advisory(ies): CVE-2014-1859 (Numpy arbitrary file write via symlink attack); CVE-2021-41495 (NumPy NULL Pointer Dereference); CVE-2021-33430 (NumPy Buffer Overflow (Disputed)) +7 more

Critical
Category
Supply Chain
Confidence
71% confidence
Finding
numpy

Known Vulnerable Dependency: pyyaml — 8 advisory(ies): CVE-2019-20477 (Deserialization of Untrusted Data in PyYAML); CVE-2020-1747 (Improper Input Validation in PyYAML); CVE-2020-14343 (Improper Input Validation in PyYAML) +5 more

Critical
Category
Supply Chain
Confidence
90% confidence
Finding
pyyaml

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal