The Agent Skills Directory

[SAFE]: The skill consists solely of natural language instructions and documentation. It contains no executable scripts, shell commands, or external dependencies.
[INDIRECT_PROMPT_INJECTION]: The skill operates on user-supplied text to perform rewrites. While this constitutes an ingestion surface, the skill does not possess any dangerous capabilities (e.g., file writes, network requests, or system command execution) that could be exploited via malicious input. The risk is negligible.
[SAFE]: No obfuscation, data exfiltration patterns, or privilege escalation attempts were found.

pink-elephant