terragrunt-validator

Fail

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The documentation in SKILL.md includes an installation command that downloads a script from https://raw.githubusercontent.com/aquasecurity/trivy/main/contrib/install.sh and pipes it directly into the shell (| sh). This download targets the official repository of Aqua Security's Trivy, a widely recognized and well-known open-source utility, representing standard installation behavior for this ecosystem.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and reviews infrastructure configurations within user-specified directories, introducing an indirect prompt injection vulnerability surface if malicious instructions are embedded within the scanned code.
  • Ingestion points: Target configuration files (*.hcl, terragrunt.hcl, *.tf) read by scripts/detect_custom_resources.py and processed via scripts/validate_terragrunt.sh.
  • Boundary markers: Absent. No specific prompt wrappers or defensive delimiters isolate the HCL file text from the agent's execution context.
  • Capability inventory: Invokes multiple system utilities (terragrunt, terraform, tflint, trivy, checkov) via shell execution paths in scripts/validate_terragrunt.sh.
  • Sanitization: Relies on structural HCL parsing and regular expression filtering without natural language sanitation mechanisms.
Recommendations
  • HIGH: Downloads and executes remote code from: https://raw.githubusercontent.com/aquasecurity/trivy/main/contrib/install.sh - DO NOT USE without thorough review
Audit Metadata
Risk Level
HIGH
Analyzed
Sep 15, 2026, 02:25 PM