The Agent Skills Directory

[SAFE]: The skill consists of natural language instructions guiding the agent through a design review process. It does not include scripts, binaries, or tool configurations that could perform actions on the system.
[DATA_EXFILTRATION]: No network requests or access to sensitive local files (such as credentials or SSH keys) are present in the skill.
[INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing external data (implementation plans). However, since the skill has no capabilities to execute code, write files, or access the network, the risk is negligible.

program-design