ClawHub
Back to skill

Security audit

stock-sentiment

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed, read-only stock sentiment API helper that uses a SentiSense API key and network calls without trading or account-changing powers.

Install only if you are comfortable sending stock ticker queries and your SentiSense API key to app.sentisense.ai. Keep the key in the environment as instructed, watch quota and rate limits, and treat outputs as market context rather than investment advice.

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
92% confidence
Finding
The skill clearly instructs use of shell, outbound network access, and an environment variable, but it does not declare corresponding permissions. That creates a trust and sandboxing gap: an agent or platform may grant or infer capabilities implicitly, making review and policy enforcement weaker than if the capabilities were explicitly declared.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.