The Agent Skills Directory

[Prompt Injection] (SAFE): No malicious instructions or attempts to bypass safety filters were detected in the skill definitions or examples.
[Data Exposure & Exfiltration] (SAFE): No access to sensitive local files or unauthorized network transmissions were identified. The code snippets focus on local unit and integration testing.
[Obfuscation] (SAFE): The content is clear and uses standard Markdown and Rust syntax without any hidden or encoded data.
[External Downloads & Remote Code Execution] (SAFE): References to external tools are limited to standard Rust development utilities (cargo) and widely-used GitHub Actions in documentation examples. No untrusted script downloads or piped execution patterns are present.
[Privilege Escalation] (SAFE): The skill does not include commands that attempt to gain administrative or root access.

gpui-test