The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional text and documentation intended to guide the agent in performing architectural reviews. There are no scripts, binaries, or tool configurations associated with the skill.
[SAFE]: No patterns of prompt injection, obfuscation, or credential harvesting were detected. The instructions are aligned with the stated purpose of providing architectural guidance.
[SAFE]: While the skill is designed to process external data (system designs and code), it lacks the capabilities (such as network access or shell execution) required for an indirect prompt injection attack to have any impact on the execution environment.

Architect Review