The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a shell command pipeline using grep and xargs to map code dependencies. The command is scoped to the project's source directory (src/) and is used for legitimate static analysis purposes during the mapping phase.
[INDIRECT_PROMPT_INJECTION]: The skill operates by ingesting and analyzing external data in the form of the user's source code. This represents an attack surface where malicious instructions embedded in comments or strings within the code could potentially influence agent behavior. However, this risk is intrinsic to the skill's primary function of code refactoring.
Ingestion points: Project source files (e.g., .js, .ts files in the src/ directory) analyzed during the mapping step.
Boundary markers: No explicit markers are defined to separate the code content from agent instructions.
Capability inventory: Execution of shell commands for analysis and the ability to propose and sequence file structure changes (deletions and moves).
Sanitization: No explicit sanitization or filtering of the analyzed source code content is described.

module-boundaries