The Agent Skills Directory

[SAFE]: A thorough analysis of the skill instructions and reference materials revealed no malicious patterns or security vulnerabilities.
[DATA_EXPOSURE]: The skill reads from local directories such as docs/ and docs/rfcs/ to collect architectural source material, which is consistent with its intended function.
[COMMAND_EXECUTION]: There are no shell commands, system calls, or script executions present in the skill.
[REMOTE_CODE_EXECUTION]: The skill does not involve any external dependencies, remote downloads, or runtime code execution.
[PROMPT_INJECTION]: No bypass attempts, role-play injections, or instructions to ignore safety protocols were found.

roadmap-doc