ClawHub
Back to skill

Security audit

Banker Memo

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed local workflow for turning existing Chinese-company raw-data files into research memo outputs, with no evidence of hidden access, persistence, or destructive behavior.

Install only if you intend to run a local financial memo workflow on a specific prepared raw-data directory. Review the generated prompt and selected paths, use trusted versions of the referenced validation/deck tools, and have a qualified human verify all estimates, valuation ranges, credit terms, and investment conclusions before relying on the output.

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
87% confidence
Finding
The skill explicitly instructs the agent to inspect local directories and files such as `raw-data/*.json`, `references/banker_prompt_template.md`, and generated outputs, which implies file-read capability. If the platform relies on declared permissions for user awareness or enforcement, omitting this declaration can cause the skill to access workspace data without transparent consent and weakens sandbox/policy controls.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.