The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes mix credo --strict and mix credo --strict --format json in the project root. While this is standard for Elixir projects, it involves direct interaction with the host shell.
[INDIRECT_PROMPT_INJECTION]: The skill's /credo fix workflow reads untrusted project source files and processes static analysis messages to perform automated refactoring and fixes. This creates a vulnerability surface for indirect prompt injection.
Ingestion points: The skill reads source code files and the output of the mix credo command, including potentially custom check messages from dependencies like ex_slop.
Boundary markers: The instructions do not define delimiters or specific safety warnings to prevent the agent from following instructions embedded within the code being analyzed.
Capability inventory: The skill has the capability to read files, write files (saving fixes), and execute shell commands (mix credo).
Sanitization: No sanitization, validation, or escaping of the input source code or analysis messages is performed before the agent uses them to determine how to rewrite the code.

credo