The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute several local development commands, including git log, cargo test, cargo clippy, and cargo mutants. These are standard operations for a software development environment.
[INDIRECT_PROMPT_INJECTION]: The skill accepts input via $ARGUMENTS which is then interpolated into shell commands. This constitutes an attack surface for command injection if the input is not sanitized by the execution environment.
Ingestion points: The $ARGUMENTS variable is used as a crate name in multiple shell commands across SKILL.md.
Boundary markers: No explicit markers or warnings are used to isolate the user-provided arguments within the shell scripts.
Capability inventory: The skill has access to the Bash tool, allowing it to read the file system and perform version control operations.
Sanitization: There is no logic within the skill to validate or escape the $ARGUMENTS string before it is passed to the shell.

crate-admit