wizard
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [DYNAMIC_EXECUTION]: The skill generates a bash script using a provided template (template.sh). The resulting script is meant to be reviewed and executed manually by the user, representing a controlled script generation workflow.
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted repository files to determine the configuration steps for the wizard, which creates an attack surface for indirect prompt injection.
- Ingestion points: The skill reads .env, .env.example, README, docker-compose* and .github/workflows/* to identify required secrets and application variables.
- Boundary markers: The instructions lack specific boundary markers or requirements to ignore instructions embedded within the processed project files.
- Capability inventory: The generated scripts are capable of writing to local environment files and interacting with the GitHub CLI (gh) to manage secrets.
- Sanitization: No validation or sanitization protocols are specified for the data extracted from the repository files before inclusion in the wizard logic.
Audit Metadata