The Agent Skills Directory

[SAFE]: The skill consists entirely of technical documentation and code reference patterns for the Phoenix framework. All code snippets follow standard development practices and do not contain any hidden commands, obfuscated content, or unauthorized network operations.
[INDIRECT_PROMPT_INJECTION]: The skill provides code templates for handling web requests which ingest untrusted user data via conn.params. However, the skill explicitly mandates the use of the Phoenix 1.8 %Scope{} pattern for every context function to enforce mandatory authorization and data isolation at the boundary. It also promotes the use of Ecto Changesets for validation and Verified Routes for safe URL generation, effectively mitigating common injection and access control risks.

phoenix-contexts