ClawHub
Back to skill

Security audit

小河狸财报助手

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed local financial-data helper that uses a limited localhost read-only API and does not show hidden persistence, credential use, external exfiltration, or destructive behavior.

Install this only if you intend your agent to answer questions using financial data from the locally running LittleBeaver Financial Assistant. Treat returned report data as private, and be aware that implicit invocation may cause the skill to be used for relevant financial questions without a separate confirmation prompt.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
86% confidence
Finding
The default prompt broadly instructs the agent to use this skill for financial data analysis without explicit trigger boundaries, confirmation requirements, or narrower task scoping. Because implicit invocation is also enabled, the skill may be activated for loosely related financial queries and expose or process sensitive localhost financial data more readily than intended.

Static analysis

No suspicious patterns detected.