The Agent Skills Directory

[SAFE]: Analysis of the skill instructions confirms they are limited to local code refactoring and cleanup tasks. The skill defines rules for the complete removal of feature-related code, including tests and documentation, which is a standard development workflow.
[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to search codebases using tools like 'rg' (ripgrep) and process the results. While this represents an ingestion surface for potential indirect prompt injection (e.g., if a codebase contains malicious identifiers designed to influence the agent), the skill itself does not facilitate this beyond standard operational scope and includes verification steps.

hard-cut