The Agent Skills Directory

[NO_CODE]: The skill consists entirely of Markdown instructions and reference materials. It does not include any scripts (Python, JavaScript, shell), binaries, or configuration files that could execute code.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process marketing assets (landing pages, emails, etc.) which are untrusted data. However, the skill has no allowed-tools and no writes permissions, meaning it cannot perform any actions based on malicious instructions embedded in the processed text. The risk is limited to the text output provided to the user.
[EXTERNAL_DOWNLOADS]: No external URLs or remote resources are referenced or downloaded. All information is contained within the skill's local files.
[CREDENTIALS_SAFE]: No hardcoded secrets, API keys, or sensitive environment variables were detected. The skill uses standard placeholder logic for brand context files.

marketing-psychology