The Agent Skills Directory

[COMMAND_EXECUTION]: The skill requires the Bash tool to perform its primary function of refactoring and running tests, which allows for arbitrary command execution on the host system.
[PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection by ingesting data from files that could contain malicious instructions. * Ingestion points: The skill uses Read, Grep, and Glob to ingest untrusted code from the filesystem. * Boundary markers: There are no markers or system instructions provided to ensure the agent treats ingested code strictly as data rather than instructions. * Capability inventory: The skill has access to Bash for shell execution and Edit for modifying the filesystem. * Sanitization: No sanitization, validation, or filtering of the content being refactored is defined.

refactor