NYC

act-workflow-syntax

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [Prompt Injection] (SAFE): No instructions attempting to override agent behavior or bypass safety filters were found. The content consists entirely of technical documentation and examples.- [Data Exposure & Exfiltration] (SAFE): The skill discusses secrets management for both GitHub Actions and local testing with 'act'. It correctly uses placeholders (e.g., 'ghp_your_token_here') and follows best practices for secret handling. No hardcoded credentials or commands to exfiltrate data were detected.- [External Downloads] (SAFE): References standard, well-known GitHub Actions from the official 'actions' organization (e.g., 'actions/checkout@v4', 'actions/setup-node@v4'). One third-party action ('dorny/paths-filter') is mentioned in an example, which is a common and reputable community action.- [Command Execution] (SAFE): Examples of 'act' and 'bash' commands are provided for educational purposes (e.g., checking environment variables or running local tests). These commands are benign and standard for the stated purpose of the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:16 PM