skills/superfly/skills/fly/Gen Agent Trust Hub

fly

Pass

Audited by Gen Agent Trust Hub on Nov 4, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions for installing the Fly.io CLI and related tools using official scripts from fly.io and sprites.dev. These domains are controlled by the vendor and are standard for the infrastructure management tasks the skill performs.
  • [COMMAND_EXECUTION]: The skill utilizes the fly CLI and remote execution tools (fly ssh, sprite exec) to manage cloud resources. These capabilities are essential to its function and are governed by extensive safety instructions and user confirmation requirements for sensitive or billable actions.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect injection as it processes external content like logs and file data. It addresses this risk through explicit boundary markers, instructing the agent to treat all external output strictly as data and never as instructions, and by providing a comprehensive safety reference (safety.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 4, 2026, 04:28 AM