ClawHub
Back to skill

Security audit

Upload Markdown to Lexiang

Security checks across malware telemetry and agentic risk

Overview

This skill does what it says: uploads user-chosen Markdown and local images to Tencent Lexiang using a disclosed personal token workflow.

Install only if you intend to let the skill store a Lexiang personal MCP token locally and create or overwrite Lexiang pages you specify. Use dry-run first for new workflows, keep the credential file private, and prefer a named profile or dedicated credential with the least Lexiang access you need.

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
88% confidence
Finding
The skill explicitly instructs callers to run local Python scripts, access environment variables, read and write credential files, use network access, and invoke shell commands, yet it declares no permissions metadata. This creates a transparency and policy-enforcement gap: users or orchestrators may approve or execute the skill without understanding that it can access local files and remote services using personal credentials.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
tests/test_lexiang_upload.py:136