building-nango-functions-locally
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to execute shell commands using the Nango CLI and Node.js tools. This includes validating logic with
nango dryrun, recording test mocks with--save, generating test suites withnango generate:tests, and deploying functions vianango deploy. - [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks because it instructs the agent to process external, potentially untrusted data (API documentation and sample responses) to generate executable TypeScript code.
- Ingestion points: The agent is required to gather "API reference URL or sample response" as inputs for function creation (found in
SKILL.md). - Boundary markers: The instructions lack explicit boundary markers or delimiters to isolate ingested external data from the agent's instructions during the code generation process.
- Capability inventory: The skill possesses the capability to write TypeScript files to the local file system and execute them using
nango dryrunandnpm test. - Sanitization: The instructions recommend using
zodfor validating inputs and outputs within the generated code, which provides some structural safety for data processing.
Audit Metadata