ClawHub

Siyuan Agent

Security checks across malware telemetry and agentic risk

Overview

This SiYuan helper appears legitimate, but it gives an agent broad authenticated power to read and change notes through a raw API command.

Install only if you are comfortable letting the agent access your SiYuan API token and note database. Keep `SIYUAN_BASE` pointed at localhost or another trusted SiYuan server, avoid the raw `call` command unless you know the exact endpoint, and require explicit confirmation before write, delete, export, or broad SQL operations.

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
96% confidence
Finding
The skill requires access to an environment variable containing a sensitive API token and performs direct HTTP requests, but it does not declare permissions for those capabilities. That mismatch weakens platform trust and review controls because the agent can access credentials and local network services without explicit permission metadata, increasing the chance of unintended data exposure or unauthorized note modification.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal