Security audit

Terradev GPU Cloud

Security checks for vulnerabilities and agentic risk

Overview

Review before installing: the skill’s cloud-management purpose is coherent, but it asks for broad cloud credentials and installs an unpinned external CLI that can manage costly infrastructure.

Install only if you trust the Terradev CLI supply chain and are comfortable granting it cloud-management authority. Prefer configuring only the provider you are actively using, use narrow or short-lived credentials, run dry-run or quote commands first, confirm every provisioning or deletion action, and monitor cloud accounts for lingering instances, clusters, deployments, and spend.

A.I.G

Vulnerability Patterns

Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Insecure DependenciesIntroduces malicious components through unsafe dependency sources
Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review

Findings (2)

T05 · Unauthorized Access and Privilege Escalation

Error

Location: SKILL.md:8
Finding: Excessive Global Exposure of Multi-Cloud Credentials
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Error

Location: SKILL.md:42
Finding: Unpinned and Unauditable Third-Party CLI Installation
Content: View full analysis
Remediation: View remediation

SkillSpector

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