Security audit

doubt-driven-develop

Security checks across malware telemetry and agentic risk

Overview

This skill is a vague development automation helper that asks for command execution and references credentials, external services, and file access without clear limits or user controls.

Review this carefully before installing. It is not proven malicious, but it asks for powerful command execution and refers to credentials and external services without explaining exactly what will run or where data goes. Only use it in a constrained environment with non-sensitive inputs unless the publisher provides a much more specific scope.

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)

Description-Behavior Mismatch

Medium

Confidence: 95% confidence
Finding: The manifest presents the skill as a generic Development/data-processing helper, but the documentation materially expands its capabilities to include external API access, filesystem interaction, and command execution. This mismatch is dangerous because users and reviewers may grant trust or permissions based on a narrower stated purpose while the skill can perform much more powerful operations.

Context-Inappropriate Capability

High

Confidence: 97% confidence
Finding: The skill declares exec capability even though its stated purpose is a generic Development workflow/data-processing helper, and no concrete need for shell access is established. Unnecessary command execution is a major risk because it can enable arbitrary local actions, data destruction, secret access, or lateral movement if the skill is used with broad permissions.

Context-Inappropriate Capability

Medium

Confidence: 92% confidence
Finding: The documentation introduces API keys, external service connections, and network access without clearly tying them to the skill's core purpose or describing limits on their use. This is dangerous because vague credentialed network behavior can facilitate unauthorized data exfiltration, misuse of third-party services, or accidental exposure of secrets.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The skill declares exec capability and discusses command execution, but the description does not clearly warn users that shell commands may be run. This increases risk because users may provide inputs or approve use under the assumption of passive processing, while the skill may actually trigger system-level actions.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The skill references API keys and external connectivity but does not give a clear warning that user data may be sent to external services or that credentials are involved. This is dangerous because it undermines informed consent, increases the chance of secret mishandling, and can expose sensitive content to third parties unexpectedly.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.