vps-deploy-executor
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to manage VPS environments, which involves executing shell commands for service management, file system operations, and proxy reloads. These actions are bounded by strict instructions to perform pre-mutation inspections and obtain explicit user consent for each step.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data sources that could be attacker-controlled.
- Ingestion points: Reads local files such as
DEPLOY.md, shell scripts, and service configurations (SKILL.md). - Boundary markers: The instructions do not specify technical delimiters for file content, but they emphasize verifying scripts rather than blindly executing them.
- Capability inventory: The agent has capabilities for command execution (via SSH), file writing, and service reloads.
- Sanitization: The skill mandates that the agent present a comprehensive plan to the user for approval before any modification occurs, serving as a manual validation layer.
Audit Metadata