devops-engineer

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill includes several automation scripts and API templates that interpolate untrusted input (like service names, versions, or environments) directly into shell commands and configuration files without sanitization.
  • Ingestion points: Arguments in create-service.sh (references/platform-engineering.md) and release.sh (references/release-automation.md), and the ServiceRequest schema in the FastAPI example (references/platform-engineering.md).
  • Boundary markers: Absent; variables are used directly in string templates and shell heredocs.
  • Capability inventory: Execution of high-privilege CLI tools including kubectl, gh (GitHub CLI), terraform, and curl across multiple reference files.
  • Sanitization: Absent; the templates do not include logic to escape or validate user-provided strings before they are used in sensitive operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 11:50 AM
Security Audit — agent-trust-hub — devops-engineer