neon
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches additional agent instructions (SKILL.md) and technical documentation from official vendor domains, including neon.com and github.com/neondatabase.
- [COMMAND_EXECUTION]: The skill uses the official 'neon' CLI to manage project infrastructure, handle authentication, and deploy serverless functions through 'neon.ts' configuration files.
- [INDIRECT_PROMPT_INJECTION]: The skill processes documentation and instructions fetched from remote URLs, which constitutes an attack surface for indirect prompt injection.
- Ingestion points: Documentation pages (neon.com/docs/*) and identity protocols (claimable.neon.tech/auth.md).
- Boundary markers: No specific delimiters or safety warnings are implemented for the fetched content.
- Capability inventory: The skill possesses extensive capabilities including shell command execution, file system access (.env, neon.ts), and credential management.
- Sanitization: No explicit sanitization or instruction filtering is performed on the ingested remote content.
Audit Metadata