ClawHub
Back to skill

Security audit

source-driven-development

Security checks across malware telemetry and agentic risk

Overview

This skill gives agents a documentation-first development workflow and does not add hidden execution, persistence, credential use, or unrelated data access.

Before installing, confirm you are comfortable with agents reading normal project dependency files and browsing official documentation to justify framework-specific code decisions. Non-Chinese users may find the current skill text harder to audit or operate because it does not provide an explicit language fallback.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The skill content is predominantly written in Chinese and does not offer a language choice, fallback, or justification for a locale-specific constraint. This can cause the agent to operate in an unexpected language, reducing user comprehension, increasing the risk of misconfiguration or misuse, and making security-relevant instructions harder for some users to verify.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.