The Agent Skills Directory

[SAFE]: The skill consists entirely of Markdown documentation and instructional content intended to guide an AI agent in code review and refactoring tasks. No executable scripts, binaries, or configuration files that could facilitate malicious actions were found.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process and refactor user-provided source code, which introduces a theoretical surface for indirect prompt injection. Malicious instructions could be embedded within code comments or string literals in the data being refactored.
Ingestion points: User-provided code snippets or files processed by the agent using the patterns described in SKILL.md and references/code-review-workflow.md.
Boundary markers: Absent. The skill does not define specific delimiters or instructions to ignore embedded prompts within the code being analyzed.
Capability inventory: The skill does not explicitly request tools, but the agent's default capabilities (file modification, terminal access) are active and could be targeted by an injection.
Sanitization: None. The skill assumes the provided code is passive data to be structured rather than untrusted input.

refactoring