neon-object-storage

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches the foundational neon skill from the official Neon documentation website to ensure environment consistency.
  • [COMMAND_EXECUTION]: Uses the neon CLI tool (a vendor-provided utility) to manage infrastructure-as-code, provision S3-compatible buckets, and manage environment variables locally.
  • [INDIRECT_PROMPT_INJECTION]: As the skill facilitates the storage and retrieval of user-generated content (images, documents, uploads), it creates a surface for indirect prompt injection where untrusted data could be ingested by an agent.
  • Ingestion points: S3 bucket objects accessed via the Files SDK or AWS S3 Client as described in SKILL.md.
  • Boundary markers: None explicitly defined in the implementation snippets.
  • Capability inventory: Performs network operations via S3 API calls and handles file writes/reads.
  • Sanitization: The skill focuses on the transport and storage layer; sanitization of object content is not addressed in the provided snippets.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 08:10 PM
Security Audit — agent-trust-hub — neon-object-storage