The Agent Skills Directory

[SAFE]: No malicious patterns or security risks were detected. The skill provides legitimate documentation and configuration examples for Fly.io.
[INDIRECT_PROMPT_INJECTION]: The skill assists in managing configuration files such as fly.toml and litefs.yml (Ingestion points). While it lacks explicit boundary markers or sanitization, its primary purpose is instructional (Capability inventory: flyctl command examples). The attack surface is minimal as it does not perform automated execution on untrusted data.
[CREDENTIALS_UNSAFE]: The skill promotes secure credential management by instructing users to use fly secrets set and specifically warning against committing secrets to version-controlled configuration files.

fly-io