The Agent Skills Directory

[SAFE]: The skill functions as a local persona generator that reads from local template files and writes output to a user-defined directory. No network activity or external data fetching is performed.
[SAFE]: No evidence of prompt injection or attempts to bypass AI safety guidelines was found. The instructions are focused on structured assembly of content.
[SAFE]: The skill does not utilize any obfuscation techniques, hidden characters, or encoded payloads.
[SAFE]: There are no external dependencies, package installations, or remote code execution patterns. It relies entirely on the built-in capabilities of the AI agent for file manipulation.
[SAFE]: The skill includes security-conscious instructions, such as explicitly warning the AI not to use data from the example-input.md file as a source for real agent generation.

lobster-agent-creator