The Agent Skills Directory

[SAFE]: The skill instructions were analyzed for prompt injection, data exfiltration, obfuscation, and other malicious patterns, and no issues were found.
[NO_CODE]: This skill consists entirely of natural language instructions and markdown templates. It does not include any scripts, binaries, or configuration files that execute commands.
[INDIRECT_PROMPT_INJECTION]: The skill receives external input through the $ARGUMENTS placeholder; however, it lacks any tool access, file system permissions, or network capabilities that could be leveraged for an attack. The attack surface is effectively zero.

agent-ux-researcher