Security audit

Code Dev V1

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed release-management helper, but users should treat its repository changes and CI/CD credentials carefully.

Install only for repositories where you want an agent to help with release work. Review any generated shell, Git, CI/CD, or deployment action before it runs, and keep CI tokens and webhook URLs in secure environment/secret storage rather than prompts or committed files.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
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)

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The skill explicitly instructs the agent to perform release-management and command-execution style operations, but it does not warn users that these actions may modify repositories, create files, tag releases, or affect deployment environments. In an agent context with exec capability enabled, this omission increases the chance of unintended system changes because users may treat the skill as advisory when it is operational.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The skill documents environment variables for CI tokens and release webhooks, but provides no warning about secret handling, redaction, storage, or avoiding disclosure in logs and outputs. In a release-oriented skill that may run commands and produce audit artifacts, this can lead to accidental exposure of deployment credentials or unsafe reuse of sensitive values.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.