NYC

artifact-management

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [Prompt Injection] (SAFE): No instructions found that attempt to override agent behavior or bypass safety filters.
  • [Data Exposure & Exfiltration] (SAFE): Examples correctly use secrets placeholders (e.g., GITHUB_TOKEN, CI_JOB_TOKEN) rather than hardcoded credentials. It explicitly advises against storing secrets in artifacts.
  • [Unverifiable Dependencies] (SAFE): Uses standard, well-known GitHub Actions from trusted sources (actions/, docker/) and official Docker base images (node:18-alpine).
  • [Command Execution] (SAFE): Scripts and configurations use standard build, tag, and publish commands (npm ci, docker build, git rev-parse) appropriate for the stated purpose.
  • [Indirect Prompt Injection] (SAFE): The skill is primarily documentation and does not define surfaces for ingesting or processing untrusted external data.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:06 PM