neon-postgres

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches current documentation and technical guides from Neon's official domain (neon.com) to ensure the agent has up-to-date information.
  • [EXTERNAL_DOWNLOADS]: References official ecosystem packages for database interaction and management, including @neondatabase/serverless, @neondatabase/neon-js, @neondatabase/auth, @neondatabase/api-client, and the neon-api Python package.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external documentation content, which presents a surface for indirect prompt injection if the source content were compromised.
  • Ingestion points: Documentation URLs located under https://neon.com/docs/ (as described in SKILL.md).
  • Boundary markers: The skill does not explicitly instruct the agent to use delimiters or ignore potential commands embedded within the fetched documentation content.
  • Capability inventory: The skill facilitates the use of the Neon CLI (neonctl) and various SDKs, which involves executing shell commands and performing network operations.
  • Sanitization: There is no evidence of content sanitization or validation for the documentation fetched at runtime.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 11:20 PM
Security Audit — agent-trust-hub — neon-postgres