ClawHub
Back to skill

Security audit

Terraform Plan Reviewer

Security checks across malware telemetry and agentic risk

Overview

This is a documented, instruction-only Terraform plan review skill, with CI workflow generation disclosed as part of its intended use.

Install this if you want help reviewing Terraform/OpenTofu/Terragrunt plans or drafting CI plan-review gates. Redact secrets and avoid pasting full state unless necessary, manually review any generated workflow or hook before committing it, and keep human approval for production or destructive applies.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Description-Behavior Mismatch

Medium
Confidence
91% confidence
Finding
The skill is presented as a terraform plan reviewer, but its documented behavior expands into generating CI workflows and automation hooks. That scope expansion is risky because users may invoke a seemingly read-only analysis skill and receive executable infrastructure automation artifacts that could be committed or run with elevated CI credentials without separate review.

Context-Inappropriate Capability

Medium
Confidence
94% confidence
Finding
The skill includes ready-to-commit GitHub Actions, GitLab CI, Atlantis, and other hook configuration generation even though its primary purpose is plan review. In a security-sensitive IaC context, emitting automation config can introduce unsafe defaults, privilege misuse, or accidental rollout of unreviewed pipeline behavior, especially if operators trust the skill as an auditor rather than as a code generator.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.