cmd-setup-workflows

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed for repository maintenance and CI/CD automation. It generates standard workflow configurations for various ecosystems (Node.js, Rust, Go, Elixir, etc.) using official, versioned GitHub Actions and established tools like the GitHub CLI.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it reads project-specific configuration files (such as package.json, Cargo.toml, and .env.test) to derive build and test commands. While malicious content in these files could theoretically influence the generated workflow, this behavior is a necessary component of the skill's primary functionality.
  • Ingestion points: Reads repository root metadata files (mix.exs, package.json, Cargo.toml, go.mod, pubspec.yaml, pyproject.toml, Makefile, flake.nix), existing workflow YAML files, and service configuration files (config/test.exs, docker-compose.yml, .env.test) in SKILL.md.
  • Boundary markers: The skill does not implement specific delimiters or instructions to isolate the content read from these files from the agent's logic.
  • Capability inventory: The skill has the capability to write files (workflow YAMLs and version updates) and execute shell commands including git and gh CLI in SKILL.md.
  • Sanitization: The skill does not explicitly validate or sanitize the data retrieved from project files before using it to construct shell commands or workflow steps.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 07:41 AM
Security Audit — agent-trust-hub — cmd-setup-workflows