The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were identified. The skill's primary function is to provide stylistic advice and recommend authorized tools for text processing.
[EXTERNAL_DOWNLOADS]: The skill recommends the @rephrasy/mcp Node.js package. This is a legitimate tool provided by the skill's author and hosted on a well-known service (NPM).
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-supplied text. However, it lacks dangerous capabilities—such as file writing, shell command execution, or network exfiltration—that would allow this data ingestion to be exploited.

bypass-pangram