skills/terminalskills/skills/act/Gen Agent Trust Hub

act

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing the act utility using Homebrew (brew install act) and references the use of standard Docker images (catthehacker/ubuntu:act-latest) to provide the environment for running workflows. Both are well-known and standard resources for this tool.
  • [COMMAND_EXECUTION]: The instructions provide several shell commands for running, listing, and debugging GitHub Actions workflows locally. These are standard operational commands for the act CLI.
  • [INDIRECT_PROMPT_INJECTION]: As a tool designed to process and execute CI/CD workflow files, act inherently ingests untrusted data in the form of YAML configurations which may contain shell commands.
  • Ingestion points: .github/workflows/*.yml files.
  • Boundary markers: None specified in instructions, though the tool uses Docker for execution isolation.
  • Capability inventory: The tool executes shell commands inside Docker containers as defined in the ingested workflow files.
  • Sanitization: Execution is isolated within Docker containers, which is a standard security practice for this use case.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 06:11 PM
Security Audit — agent-trust-hub — act