The Agent Skills Directory

[SAFE]: No security issues were identified in the skill instructions or evaluation data. The skill is purely instructional and focused on architectural evaluation.
[COMMAND_EXECUTION]: The skill does not perform any shell command execution or system-level operations. It uses character-based diagrams for visualization, which are inert.
[EXTERNAL_DOWNLOADS]: The skill does not download external scripts, packages, or configurations. All logic is contained within the prompt instructions.
[DATA_EXFILTRATION]: No network operations or patterns associated with data exfiltration were detected. The skill operates on technical design data provided in the conversation context.
[PROMPT_INJECTION]: The instructions do not contain any patterns attempting to override agent safety guidelines or system prompts. It follows a structured template for technical analysis.

decision-evaluation