Security audit

ai-report-free

Security checks across malware telemetry and agentic risk

Overview

This finance-analysis skill is not clearly malicious, but it asks for broad command-execution authority and discusses external financial APIs without enough scoping or disclosure.

Review this skill before installing. Use it only in an environment where command execution is sandboxed or requires explicit confirmation, do not run it with administrator privileges, and avoid sending proprietary financial reports or credentials to external data APIs unless you have confirmed the data-flow and privacy controls.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Intent-Code Divergence

Medium

Confidence: 88% confidence
Finding: The skill repeatedly claims that risky code was removed and safety was improved, yet later content discusses command execution, admin-level operation, and long-running commands. This contradiction can mislead users and downstream agents into granting more trust than warranted, increasing the chance that dangerous execution features are used without appropriate scrutiny.

Description-Behavior Mismatch

Medium

Confidence: 93% confidence
Finding: The manifest presents the skill as a finance analysis tool but declares a generic exec capability without scoping it to narrowly defined finance tasks. Broad execution access in a domain-specific skill creates unnecessary attack surface and could enable arbitrary local command execution if an agent trusts the manifest.

Context-Inappropriate Capability

Medium

Confidence: 91% confidence
Finding: The troubleshooting guidance explicitly references command execution and even suggests administrator-level runs, despite the stated purpose being financial-report analysis. Normalizing elevated or unrestricted execution in documentation can prompt unsafe agent behavior and expose the host to privilege misuse or arbitrary command abuse.

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The skill describes API-based integration and external financial data sources but does not clearly warn that user-supplied financial/report data may be transmitted to third-party services. This creates a data handling transparency issue and can lead to unintended disclosure of sensitive business information.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The manifest advertises exec capability and the document later discusses command execution, but there is no prominent warning that the skill may run commands on the user's system. Lack of clear disclosure can cause users or orchestrators to invoke the skill with insufficient safeguards, enabling potentially harmful local actions.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.