The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions and markdown templates for a marketing assessment framework. No executable code or scripts are present in the package.
[NO_CODE]: All logic is implemented via prompt instructions; there are no Python, JavaScript, or shell scripts that could execute malicious commands.
[INDIRECT_PROMPT_INJECTION]: While the skill ingests untrusted user data about marketing channels in references/full-guide.md, it possesses no exploitable capabilities such as file system writes, network requests, or subprocess execution that could be targeted by an injection attack.

channel-validator