neon-object-storage
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by facilitating the ingestion of external data from S3-compatible buckets and local configuration files.
- Ingestion points: The agent reads from
neon.tsfor infrastructure configuration and environment variables for credentials. It also handles data downloaded from S3 buckets through methods likefiles.download()orGetObjectCommand. - Boundary markers: No specific boundary markers or instructions to treat external data as untrusted are explicitly provided in the implementation examples.
- Capability inventory: The skill enables infrastructure modification via
neon deployand file system/network operations through S3 client commands (upload, download, delete). - Sanitization: The instructions do not include explicit sanitization or validation logic for data retrieved from object storage before it is processed by the agent or application.
Audit Metadata