boxlang-runtime-github-actions

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documents the use of the ortus-boxlang/setup-boxlang GitHub Action to install the BoxLang runtime. This represents standard vendor-provided functionality for CI/CD environments.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides templates that ingest and execute project-specific code within a CI/CD context. This represents an attack surface where malicious project code could influence the pipeline, though it is standard for CI/CD operations.
  • Ingestion points: The workflow templates process local repository files through the actions/checkout step.
  • Boundary markers: Commands are delimited within standard YAML run blocks.
  • Capability inventory: The templates perform file system access, network operations for module installation via ForgeBox, and subprocess execution using the boxlang and box CLI tools.
  • Sanitization: The skill relies on standard CI/CD security models where project code is executed within the isolated runner environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 09:01 AM
Security Audit — agent-trust-hub — boxlang-runtime-github-actions