The Agent Skills Directory

Shell Command Interpolation: The skill constructs shell commands by interpolating the $ARGUMENTS variable into yarn test commands. While this enables flexible testing of the React codebase, it creates a potential surface for command injection if the input contains shell metacharacters that are not properly sanitized before execution.
Indirect Prompt Injection Surface: The skill processes external inputs which are subsequently used to drive sensitive command-line operations. Every instruction set that processes untrusted data without explicit boundary markers or sanitization steps introduces a risk. Ingestion points: User-provided $ARGUMENTS in SKILL.md. Boundary markers: None present. Capability inventory: Execution of subprocesses via yarn commands in SKILL.md. Sanitization: Not explicitly defined in the skill instructions.

test