iac-misconfig-scan

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of instructions for the AI to perform a diagnostic review of local configuration files. It does not include any executable scripts or network-active code.
  • [EXTERNAL_DOWNLOADS]: References the vendor's website at qualitymax.io for further security services. This is a legitimate vendor resource.
  • [PROMPT_INJECTION]: The skill interacts with untrusted external data by scanning user-provided configuration files, which presents an indirect prompt injection surface.
  • Ingestion points: Reads IaC files including Dockerfile, docker-compose.yml, *.tf, and .github/workflows/*.yml.
  • Boundary markers: The instructions do not provide explicit delimiters to separate untrusted file content from the agent's instructions.
  • Capability inventory: The skill is read-only and diagnostic; it does not possess file-writing, shell execution, or network exfiltration capabilities.
  • Sanitization: The agent processes the raw content of the target files for analysis without sanitization filters.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 04:06 PM
Security Audit — agent-trust-hub — iac-misconfig-scan