detecting-infrastructure-drift

Pass

Audited by Gen Agent Trust Hub on Jul 21, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses dynamic context injection (the ! syntax) in SKILL.md to display the environment state when the skill is loaded. These commands (ls, terraform version) are benign and used for environment discovery. It also includes a shell script scripts/drift-check.sh that executes infrastructure management tools (terraform, pulumi). These operations are consistent with the skill's stated purpose of infrastructure drift detection.
  • [SAFE]: The skill explicitly advises using read-only IAM permissions for the cloud provider and suggests using standard authentication methods (aws configure, gcloud auth login), which aligns with security best practices for monitoring tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 21, 2026, 11:30 AM
Security Audit — agent-trust-hub — detecting-infrastructure-drift