ClawHub
Back to skill

Security audit

wealth-innovation-briefing

Security checks across malware telemetry and agentic risk

Overview

This skill generates a financial briefing PDF using disclosed local files and a browser renderer, with no evidence of hidden data theft or destructive behavior.

Install only if you are comfortable with the agent creating local briefing files and launching local Chromium to render a PDF. Before running, adjust the output paths to a dedicated folder and avoid using broad automation memory for full briefing contents.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill instructs the agent to read and write local files (`content_<日期>.py`, `build_<日期>.py`, `briefing.html`, `memory.md`) without declaring corresponding permissions. Undeclared filesystem access weakens trust boundaries and can lead to unintended reads or overwrites if the runtime grants broader file access than users expect.

Tp4

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding
The skill claims to generate a briefing PDF, but its instructions also include launching a locally installed Chromium executable, traversing local filesystem paths, and depending on hard-coded host-specific locations. This mismatch is dangerous because users may approve a content-generation skill without realizing it performs broader local execution and file access, increasing the risk of unintended system interaction or abuse of local resources.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.