The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external code provided by users for refactoring, which introduces a vulnerability to instructions embedded within that code.
Ingestion points: User-provided code snippets intended for refactoring as described in SKILL.md and the usage examples in README.md.
Boundary markers: The instructions lack explicit delimiters or specific directives for the agent to ignore or sanitize instructions that might be embedded within the code blocks it is asked to refactor.
Capability inventory: The skill's configuration in SKILL.md allows access to high-privilege tools including Write, Edit, and Bash.
Sanitization: There is no documented mechanism for validating, filtering, or escaping the content of the code snippets before they are processed by the agent's logic.

refactoring-specialist