ClawHub
Back to skill

Security audit

AIsa Financial Data

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward financial-data skill that uses a user's AISA API key to query the documented AIsa market-data API.

Install only if you trust AIsa with your API key and the market symbols, screening filters, date ranges, and portfolio-style queries you submit. Treat AISA_API_KEY as a secret, monitor API usage costs, and avoid sending confidential trading strategies, client identifiers, or private portfolio details unless that third-party sharing is acceptable.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill metadata declares required environment variables and binaries and clearly demonstrates outbound network access, but there is no explicit permissions declaration to make those capabilities visible to users or policy systems. This creates a transparency and governance gap: a user may invoke the skill without realizing it can read an API key from the environment and transmit requests to an external service.

Missing User Warnings

Low
Confidence
93% confidence
Finding
The skill repeatedly instructs authenticated requests to a third-party API and encourages user-driven queries, but it does not clearly warn that ticker selections, query parameters, and potentially prompt-derived inputs will be sent to api.aisa.one. This is a privacy and informed-consent issue: even if the data is often non-sensitive market data, user interests, watchlists, or research topics may still be externally disclosed.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.