castai-install-auth

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill configured the environment to fetch Helm charts from the official CAST AI GitHub Pages repository (https://castai.github.io/helm-charts).
  • [COMMAND_EXECUTION]: The skill uses shell commands for Helm, Kubectl, and Terraform to manage cluster resources and agent deployments, which are necessary for its primary purpose of cluster onboarding.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources that could potentially contain instructions.
  • Ingestion points: The skill reads Kubernetes pod status via kubectl get pods and cluster information via curl requests to the CAST AI API (SKILL.md).
  • Boundary markers: The instructions do not define explicit boundary markers or delimiters for the data returned by these tools.
  • Capability inventory: The skill has extensive capabilities including shell command execution (helm, kubectl, terraform), file reading, and file writing (SKILL.md).
  • Sanitization: There is no evidence of specific sanitization or validation of the data received from external tool outputs before it is processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 03:01 AM
Security Audit — agent-trust-hub — castai-install-auth