skills/crafter-station/vps-cli/vps/Gen Agent Trust Hub

vps

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the vps CLI tool to perform server management operations, including creating projects, deploying applications, and managing database instances.
  • [EXTERNAL_DOWNLOADS]: The skill references container images for databases (PostgreSQL, MySQL, Redis, MongoDB) from official registries and LibSQL from the GitHub Container Registry (ghcr.io/tursodatabase/libsql-server).
  • [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it processes data retrieved from a remote VPS.
  • Ingestion points: Data enters the context via output from vps project list, vps app info, and database list/info commands.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded content are provided in the instructions.
  • Capability inventory: The skill can execute various server management subcommands through the vps CLI.
  • Sanitization: No sanitization or validation of the VPS output is performed before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 05:14 AM
Security Audit — agent-trust-hub — vps