Codemagic

Security checks across malware telemetry and agentic risk

Overview

This Codemagic skill appears legitimate, but it gives an agent broad authenticated CI/CD control without enough built-in safeguards for disruptive actions.

Install only if you intend to let an agent operate your Codemagic account through Membrane. Use a least-privileged or test Codemagic workspace where possible, and require explicit approval before deleting caches, starting or canceling builds, adding apps, creating public artifact URLs, or using raw proxy requests.

SkillSpector

By NVIDIA

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

Confidence: 88% confidence
Finding: The skill advertises destructive operations like deleting caches and canceling builds without any warning, confirmation requirement, or guidance to verify user intent. In an agent-driven environment, this increases the chance that a vague or misinterpreted request leads to irreversible or service-impacting actions.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal