okteto-onboarding

Pass

Audited by Gen Agent Trust Hub on Jul 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or critical security vulnerabilities were detected. The skill automates legitimate development workflows using official vendor tools and follows a transparent process for creating and validating project configurations.\n- [PROMPT_INJECTION]: The skill analyzes untrusted repository files (e.g., package.json, docker-compose.yml, Dockerfile) to generate configuration. While this creates a theoretical surface for indirect prompt injection, it is the intended functionality of an onboarding tool.\n
  • Ingestion points: Processes project artifacts including docker-compose.yml, Helm charts, Kubernetes manifests, and language-specific manifests (package.json, go.mod, pom.xml, pyproject.toml, etc.).\n
  • Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore' instructions for the content of processed files.\n
  • Capability inventory: Executes okteto build, okteto deploy, git push, and gh pr create via subprocess calls.\n
  • Sanitization: Absent. Content from analyzed files is used to model the project and generate the Okteto manifest without explicit escaping or validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 24, 2026, 08:50 AM
Security Audit — agent-trust-hub — okteto-onboarding