The Agent Skills Directory

[COMMAND_EXECUTION]: The skill describes execution of a CLI tool named recall via shell commands. It interpolates user-provided content directly into these commands, which could lead to command injection if the underlying agent does not properly escape characters like backticks, semicolons, or pipes.
[PROMPT_INJECTION]: The skill acts as an ingestion point for untrusted user data that is stored in a persistent memory system, creating an indirect prompt injection surface.
Ingestion points: User-supplied strings in SKILL.md used for placeholders like <content>, <problem>, <solution>, and <why>.
Boundary markers: Absent. The instructions do not specify delimiters or warnings to prevent the agent from interpreting stored data as future instructions.
Capability inventory: The skill is capable of shell command execution through the recall utility.
Sanitization: Absent. There is no logic provided to sanitize or validate user input before it is passed to the shell or stored in the memory database.

recall-add