ClawHub
Back to skill

Security audit

Sharesight Skill for OpenClaw

Security checks across malware telemetry and agentic risk

Overview

This Sharesight skill is a disclosed finance API tool that uses Sharesight credentials and can modify records only after an explicit write-mode opt-in.

Install only if you intend to connect an agent or CLI to your Sharesight account. Leave SHARESIGHT_ALLOW_WRITES unset for read-only use, enable it only when you need changes, review create/update/delete commands carefully, and clear the cached token when the integration is no longer needed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding
The skill exposes sensitive capabilities including environment variable access, shell execution, network access, and file writing, but does not declare explicit permissions boundaries. In a finance-related skill handling API credentials and portfolio data, this weakens trust and reviewability because the agent could access secrets or perform external actions without a clearly stated security contract.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The documentation includes delete operations for holdings, investments, prices, and coupon rates without prominent warnings that these actions may be irreversible or materially affect financial records. In a portfolio-management context, accidental execution could cause loss of investment data integrity and operational disruption, especially if write mode is enabled.

Credential Access

High
Category
Privilege Escalation
Content
)

    if response.status_code != 200:
        raise ValueError(f"Failed to get access token: {response.status_code} - {response.text}")

    token_data = response.json()
    access_token = token_data["access_token"]
Confidence
89% confidence
Finding
On token request failure, the code raises an exception including `response.text`. OAuth/token endpoints often include diagnostic details, and some providers may echo sensitive request context or internal error information. In an agent or CLI environment, this can leak secrets or authentication metadata into logs, telemetry, or user-visible error channels.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.