The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted user queries to generate philosophical responses. However, it lacks high-risk capabilities such as network access, file writing, or shell execution that would permit exploitation. The instructions also include a 'Honesty Boundaries' section that provides guidance on ethical limits and safety.
[COMMAND_EXECUTION]: The README.md provides an installation command npx skills add nuwa-skills/montaigne-skill. This is a standard user-initiated command for the skill's execution environment and targets the vendor's own repository (nuwa-skills), which is consistent with the skill's authorship.
[NO_CODE]: The skill package contains only Markdown files for instructions, examples, and research references. It does not include any executable scripts or binaries, minimizing the attack surface.

montaigne-perspective