github-actions

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates the creation and review of GitHub Actions workflow files, creating a surface for indirect prompt injection if malicious instructions are embedded in the processed files.
  • Ingestion points: Processes existing YAML files in the .github/workflows/ directory.
  • Boundary markers: Lacks explicit delimiters to separate untrusted file content from system instructions.
  • Capability inventory: Provides instructions for the agent to write and configure CI/CD workflows, which determine how code is built and deployed.
  • Sanitization: No validation or filtering of workflow content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 12:47 AM
Security Audit — agent-trust-hub — github-actions