The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run cargo check and cargo test. These commands execute the Rust compiler and test runner on the local system to verify the newly created command files.
[PROMPT_INJECTION]: There is a risk of indirect prompt injection because the skill accepts user-provided command names and descriptions to generate source code. A malicious user could provide input designed to produce dangerous Rust code—such as code that performs unauthorized file access or network operations—which would then be executed during the cargo test phase.
Ingestion points: User-supplied command name and functional description (SKILL.md).
Boundary markers: Absent; the skill does not define specific delimiters or instructions to ignore embedded commands in the user input.
Capability inventory: The skill allows writing to the filesystem (src/commands/, src/main.rs, etc.) and executing shell commands (cargo).
Sanitization: Absent; the skill does not include steps to validate or sanitize the user-provided logic before incorporating it into the Rust templates.

add-command