rayfin-getting-started
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- Command Execution: The skill uses
npxandnpmto initialize new projects and install framework components. These operations are essential for the skill's primary function of scaffolding new applications. - External Downloads: Project templates are retrieved from the vendor's official GitHub repository, and packages are fetched from the standard registry. This ensures that the environment is set up with authoritative resources.
- Indirect Prompt Injection Surface: The skill instructs the agent to read and adopt instructions from files generated during the setup process, such as
.agents/skills/rayfin/SKILL.mdandAGENTS.md. - Ingestion points: Processes instructions from
.agents/skills/rayfin/SKILL.mdandAGENTS.mdlocated in the new project directory. - Boundary markers: Not explicitly defined in the transition instructions.
- Capability inventory: The skill utilizes shell command execution via
npxandnpmfor environment configuration. - Sanitization: The skill relies on the integrity of the vendor-provided scaffolding tools and templates.
Audit Metadata