The Agent Skills Directory

[SAFE] (SAFE): No malicious patterns or security vulnerabilities were detected. The skill follows best practices for development, such as recommending backups before making changes.
[COMMAND_EXECUTION] (LOW): The skill includes bash snippets for backing up files (cp) and committing changes (git). These are standard operations for its intended purpose and do not represent a privilege escalation risk.
[INDIRECT_PROMPT_INJECTION] (LOW):
Ingestion points: The skill is designed to read and modify other skill files located in the .claude/skills/ directory.
Boundary markers: No specific delimiters are used to wrap the content of the skills being updated.
Capability inventory: The skill uses Read, Write, Edit, and Bash tools to manipulate local files.
Sanitization: The workflow relies on a 'Validate Changes' step (using an external skill-validator) to ensure integrity rather than input sanitization.

skill-updater