checking-infrastructure-compliance

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, data exfiltration, or unauthorized privilege escalation attempts were detected. The skill's functionality aligns with its stated purpose of infrastructure auditing.
  • [PROMPT_INJECTION]: The skill is designed to ingest and analyze infrastructure-as-code files (Terraform, Kubernetes, CloudFormation), which represents a surface for indirect prompt injection. However, this is a functional requirement for compliance auditing.
  • Ingestion points: Project files read during directory traversal in scripts/compliance_scan.sh and by external scanners.
  • Boundary markers: No specific delimiters or "ignore instructions" markers are implemented in the provided script logic.
  • Capability inventory: The skill possesses extensive capabilities including file system access (Read, Write, Edit), Grep, and Bash shell execution via the agent.
  • Sanitization: The utility scripts process file metadata and JSON structure without specific sanitization of embedded string content.
  • [COMMAND_EXECUTION]: The assets/compliance_rules.json configuration includes Python code snippets for specific check logic. This represents a modular architecture for security scanning rather than a malicious execution vector, as the scripts are local assets provided within the skill package.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 10:09 PM
Security Audit — agent-trust-hub — checking-infrastructure-compliance