neon-postgres-branches
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill interacts exclusively with official Neon resources, including the
neonCLI tool, the@neon/configNPM package, and documentation hosted onneon.com. These are verified resources provided by the vendor,neondatabase. - [INDIRECT_PROMPT_INJECTION]: The skill identifies a data ingestion surface where user-supplied branch names or project IDs are used in shell commands and file-writing operations (updating
.envfiles). - Ingestion points: User-provided inputs for placeholders like
<branch-name>and<project-id>inSKILL.md. - Boundary markers: The instructions include a clear directive to the agent: "Never overwrite an existing env key without explicit confirmation."
- Capability inventory: The skill uses the
neonCLI for branch management and has the ability to write connection strings to local environment files. - Sanitization: Security is maintained through a mandatory human-in-the-loop confirmation step before any file system modifications occur.
Audit Metadata