ClawHub
Back to skill

Security audit

行情研判（云端版）

Security checks across malware telemetry and agentic risk

Overview

This finance skill has a coherent purpose, but it needs Review because it exposes an API key and can read portfolio data and upload reports without a clear per-run consent gate.

Install only if you intend this skill to access your IMA holdings/watchlist folder, use external market-data/search services, and save the generated report to IMA. Replace the published MX_APIKEY with your own securely stored key, and add or require a confirmation step before holdings access and report upload, especially for scheduled cloud runs.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Context-Inappropriate Capability

Medium
Confidence
99% confidence
Finding
The skill embeds a concrete API key value directly in setup instructions, which exposes a credential to every reader and encourages reuse of a shared secret. Exposed API keys can be abused for unauthorized API consumption, quota exhaustion, billing impact, and access to any data or actions permitted by that key.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger phrases are broad enough to match ordinary finance conversations, which can cause the skill to activate unexpectedly. Because this skill reads holdings/watchlists and uploads reports, accidental activation can lead to unintended data access and external transmission without clear user intent in that specific conversation.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill instructs the agent to read portfolio/watchlist files from the IMA knowledge base and upload a synthesized report, but it does not require explicit informed consent at the point of access or transmission. This creates a privacy and data-governance risk because sensitive financial positions may be processed and persisted automatically.

Ssd 3

High
Confidence
99% confidence
Finding
A hardcoded API key in natural-language instructions is a direct secret exposure. Even if intended as convenience, publishing a live credential in a widely installable skill substantially increases the chance of credential theft, abuse, and lateral misuse across dependent services.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.