The Agent Skills Directory

[SAFE]: The skill configuration is purely instructional and metadata-based. It contains no scripts, binaries, or command-line operations that could interact with the host system or network.
[PROMPT_INJECTION]: No attempts to override agent behavior, bypass safety filters, or extract system prompts were detected in the instructions.
[DATA_EXFILTRATION]: There are no network operations, hardcoded credentials, or instructions to transmit data to external sources.
[EXTERNAL_DOWNLOADS]: The skill does not reference or attempt to download any external packages, scripts, or assets.
[COMMAND_EXECUTION]: No shell commands, subprocess calls, or privilege escalation patterns (like sudo) are present.

architecture-advisor