The Agent Skills Directory

[Prompt Injection] (SAFE): No malicious override or bypass patterns detected. Instructional language is used appropriately for its stated design purpose.- [Data Exposure & Exfiltration] (SAFE): No network requests or access to sensitive file paths identified.- [Unverifiable Dependencies] (SAFE): No external package installations or remote script executions.- [Indirect Prompt Injection] (LOW): The skill ingests untrusted data from the thread or codebase to perform design analysis. However, it lacks exploitable capabilities like file-system writing or outbound network calls, and explicitly includes human-in-the-loop checkpoints by requiring clarifying questions for low-confidence scenarios.- [No Code] (SAFE): This skill contains no executable scripts or command-line operations.

impeccable-quieter