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