The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown-based instructions for product positioning and messaging. It contains no executable scripts, shell commands, or binaries.\n- [SAFE]: No network activity, external downloads, or remote code execution patterns are defined. All tasks are cognitive and performed by the AI within its output context.\n- [SAFE]: The skill does not access sensitive file paths, environment variables, or hardcoded credentials.\n- [SAFE]: Although the skill processes external product descriptions, it lacks any functional capabilities (such as file writing or network transmission) that could be exploited through indirect prompt injection.

messaging-strategy