The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and refactor external codebases, which creates a surface where malicious instructions embedded in the code could potentially influence the agent's behavior.
Ingestion points: External source code files (referenced as "Existing codebase to refactor" in SKILL.md).
Boundary markers: The instructions lack explicit delimiters or warnings to treat the ingested code strictly as data.
Capability inventory: The skill documents the use of shell commands including npx, find, git, node, and python for analysis and profiling.
Sanitization: No sanitization, validation, or filtering of the external code content is defined.
[COMMAND_EXECUTION]: The skill documentation provides specific shell commands for the agent or user to execute when performing code analysis.
Evidence: SKILL.md includes examples for npx ts-prune, npx purgecss, npx depcheck, find, git log, node --prof, and python -m cProfile.

code-refactorer