The Agent Skills Directory

[SAFE]: The skill integrates with the 'githits' CLI, which is the primary vendor tool for this skill author. Commands like githits pkg info and githits pkg vulns are used for package intelligence and security auditing.
[SAFE]: The skill contains explicit instructions in the 'External Content Posture' section for the agent to treat all data from remote repositories and registries as untrusted third-party evidence. It explicitly warns against adopting embedded directions, URLs, or commands found in retrieved content.
[SAFE]: Credentials management follows best practices by instructing the agent to use githits login or environment variables (GITHITS_API_TOKEN) rather than hardcoding or exposing secrets.
[SAFE]: Indirect prompt injection risks are mitigated by the explicit requirement to verify claims against structured tool-owned fields rather than relying on natural language descriptions from external sources.

githits-package