setup-project
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches normative rules and best practices from the The-Focus-AI/standards repository on GitHub.
- [REMOTE_CODE_EXECUTION]: Installs agent skills from remote repositories using the skills CLI tool, typically following a locked set of definitions.
- [COMMAND_EXECUTION]: Executes shell commands via mise, pnpm, and git to configure the project environment, initialize repositories, and manage dependencies.
- [DATA_EXFILTRATION]: Uses fnox and 1Password for secret management, specifically instructing the agent to never hardcode credentials and instead use vault item mappings.
- [PROMPT_INJECTION]: Ingests external instructions from the The-Focus-AI/standards repository (Ingestion points) which are processed to guide project setup; it lacks explicit delimiters or sanitization for these external files (Boundary markers, Sanitization), while possessing shell and file system capabilities (Capability inventory).
Audit Metadata