The Agent Skills Directory

[SAFE] (SAFE): No malicious patterns, obfuscation, or persistence mechanisms were detected. The content is purely informational documentation.
[Indirect Prompt Injection] (LOW): The skill utilizes tools like Read, Grep, and Glob to ingest and analyze external source code. This creates a surface for indirect prompt injection if the processed data contains malicious instructions. However, the skill lacks high-risk capabilities such as command execution or network access, which limits the potential impact. No explicit boundary markers or sanitization logic are defined in the skill file.

safety-critical-patterns