building-nango-functions-locally
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local shell commands using the Nango CLI (such as 'nango dryrun', 'nango generate:tests', and 'nango deploy') and 'npm test' to facilitate the development, validation, and deployment of integration scripts. These operations are the primary intended purpose of the skill for developer productivity.- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection through the ingestion of external API documentation and sample responses.
- Ingestion points: External API reference URLs and sample response payloads are requested as inputs in SKILL.md.
- Boundary markers: No explicit boundary markers or 'ignore embedded instructions' directives are specified for the ingested data.
- Capability inventory: The skill can write files to the local filesystem and execute shell commands through the Nango CLI.
- Sanitization: No explicit sanitization or validation of the external content is performed before it is used to generate code.
Audit Metadata