ci-verify-setup

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security vulnerabilities were detected. The skill uses well-known and trusted GitHub Actions (actions/checkout and oven-sh/setup-bun) to automate a standard development workflow.
  • [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection because it must analyze untrusted project configuration files to generate a verification pipeline.
  • Ingestion points: The agent reads existing scripts and metadata from files such as package.json and lockfiles.
  • Boundary markers: No explicit markers are used to isolate untrusted project data from instructions.
  • Capability inventory: The skill is capable of modifying local project files and executing a generated 'verify' script.
  • Sanitization: The skill does not explicitly sanitize or validate the contents of existing scripts before incorporating them into the verify command.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 07:19 AM
Security Audit — agent-trust-hub — ci-verify-setup