The Agent Skills Directory

[SAFE]: The skill performs expected operations for a technical director role, such as reading project documentation and writing architecture blueprints. No suspicious file access or network activity was detected.
[COMMAND_EXECUTION]: The skill is granted access to the Bash tool, but the provided instructions do not include any automated or hidden command execution patterns. Its usage is restricted to standard development tasks.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources like Game Design Documents (GDDs) and engine references. While this presents a potential surface for indirect prompt injection if those files contain malicious instructions, the skill's design requires explicit user approval at every phase of the architecture creation, mitigating the risk of automated exploitation.

create-architecture