The Agent Skills Directory

[SAFE]: The skill operates locally by reading project directory structures and dependency manifests to generate architectural diagrams and reports. It uses standard tools like glob and grep for static analysis. There are no network-bound operations, credential access attempts, or obfuscated payloads. While the skill processes user-provided source code, the lack of high-risk capabilities like network access or system-wide file writes limits the potential impact of indirect prompt injection to a negligible level.

brooks-audit