Back to skill

Security audit

claimable-postgres

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward guide for provisioning temporary Neon Postgres databases, with credential-writing and automation disclosed as part of that purpose.

Before installing, be aware that using this skill can create temporary external Postgres databases and write connection strings into local .env files. Use it for development or test work, confirm the target env file/key, and make sure env files are ignored by version control.

Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
| Option                  | Alias | Description                                                           | Default        |
| ----------------------- | ----- | --------------------------------------------------------------------- | -------------- |
| `--yes`                 | `-y`  | Skip prompts, use defaults                                            | `false`        |
| `--env`                 | `-e`  | .env file path                                                        | `./.env`       |
| `--key`                 | `-k`  | Connection string env var key                                         | `DATABASE_URL` |
| `--prefix`              | `-p`  | Prefix for generated public env vars                                  | `PUBLIC_`      |
Confidence
74% confidence
Finding
The skill recommends using `--yes` to skip interactive prompts and proceed with provisioning automatically. Although convenient, this can cause the agent to create external resources and write credentials to local files without an explicit per-action user approval step, increasing the risk of unintended side effects.

Credential Access

High
Category
Privilege Escalation
Content
| Option                  | Alias | Description                                                           | Default        |
| ----------------------- | ----- | --------------------------------------------------------------------- | -------------- |
| `--yes`                 | `-y`  | Skip prompts, use defaults                                            | `false`        |
| `--env`                 | `-e`  | .env file path                                                        | `./.env`       |
| `--key`                 | `-k`  | Connection string env var key                                         | `DATABASE_URL` |
| `--prefix`              | `-p`  | Prefix for generated public env vars                                  | `PUBLIC_`      |
| `--seed`                | `-s`  | Path to seed SQL file                                                 | none           |
Confidence
82% confidence
Finding
The skill instructs the CLI to write database connection strings into `.env` by default, which creates and stores live credentials on disk. In an agent context, this is sensitive because secrets may be written to an unexpected file, later committed, or exposed through tooling, especially when paired with automated execution.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.