ClawHub
Back to skill

Security audit

yanlin-report-gen

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed report generator that reads user-provided JSON data and writes a local Markdown report.

Install only if you expect a local report-generation skill. Use explicit input JSON paths and an output directory you are comfortable writing to; use standalone mode only when the related Yanlin data-collection skills are installed and trusted.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill describes invoking a local Python script that reads multiple input JSON files and writes generated reports to an output directory, but it does not declare any permissions for file access. Undeclared file read/write capabilities weaken least-privilege controls and can cause operators or policy engines to underestimate what the skill can access or modify.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.