The Agent Skills Directory

[SAFE]: The skill is a collection of instructional Markdown playbooks and routing logic designed to help developers optimize their software for AI agent consumption. No malicious patterns or security risks were identified.
[COMMAND_EXECUTION]: The repository contains a shell script evals/run-static-checks.sh which is used exclusively for development-time maintenance and static analysis of the skill's structure. It does not perform any network operations, access sensitive files, or execute untrusted code.
[INDIRECT_PROMPT_INJECTION]: Although the skill is designed to ingest and review untrusted data from third-party repositories (such as SDK code and documentation), it lacks high-risk capabilities like arbitrary code execution or network exfiltration that would allow for exploitation via indirect prompt injection. The skill serves as a passive analytical tool.

design-for-agent-users