building-with-tambo
Pass
Audited by Gen Agent Trust Hub on Apr 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs legitimate integration tasks for the Tambo platform.
- [COMMAND_EXECUTION]: The skill executes standard package manager commands (npm, yarn, pnpm) and the vendor's official CLI (npx tambo) to install dependencies and configure the project. These actions are aligned with the skill's purpose and are performed in a transparent manner.
- [DATA_EXFILTRATION]: Sensitive credentials like API keys are managed using framework-specific environment variables. The authentication process utilizes a standard CLI-to-browser flow that does not involve unsafe data handling.
- [PROMPT_INJECTION]: The skill identifies a potential indirect prompt injection surface through the ingestion of untrusted project configuration and source files. 1. Ingestion points: Project configuration files (e.g., package.json, tsconfig.json) and React component source code. 2. Boundary markers: None identified in the prompt instructions. 3. Capability inventory: Shell execution for package management and CLI initialization, and file creation for providers and registries. 4. Sanitization: This risk is mitigated by a mandatory 'Confirm with User' step that gates all automated modifications and command executions.
Audit Metadata