ideogram-ci-integration

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS] (SAFE): The skill references official GitHub Actions (actions/checkout@v4, actions/setup-node@v4) which are standard, trusted components for CI/CD workflows.
  • [COMMAND_EXECUTION] (SAFE): The use of the Bash(gh:*) tool is limited to setting repository secrets (gh secret set), which is the intended and secure method for managing sensitive credentials like API keys in GitHub.
  • [CREDENTIALS_UNSAFE] (SAFE): The skill correctly demonstrates the use of placeholders (e.g., "sk_test_***") and environment variables (${{ secrets.IDEOGRAM_API_KEY }}) rather than hardcoding actual sensitive credentials.
  • [INDIRECT_PROMPT_INJECTION] (LOW):
  • Ingestion points: The skill writes to CI/CD configuration files (.github/workflows/ideogram-integration.yml).
  • Boundary markers: None present.
  • Capability inventory: Includes file writing (Write/Edit) and GitHub CLI access (Bash(gh:*)).
  • Sanitization: None present. While this creates a surface for indirect injection if an attacker could control the skill's input, the provided templates are safe and follow security best practices.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:47 PM