The Agent Skills Directory

[SAFE]: The skill consists of Markdown and YAML configuration files providing design patterns for in-product monetization. It does not include any executable scripts, binaries, or shell commands.
[INDIRECT_PROMPT_INJECTION]: The skill identifies an ingestion surface for untrusted data by directing the agent to read context from local files such as .agents/product-marketing.md. Boundary markers are present in the form of a 'Self-Critique Gate' and 'Boundaries' section in SKILL.md, which provide safety constraints and discourage unethical monetization practices. The skill's capability inventory is limited to generating text-based recommendations and interface copy, and while no explicit sanitization is performed on ingested content, the risk remains low due to the instructional scope of the skill.
[EXTERNAL_DOWNLOADS]: The skill contains references to documentation and security contact information at suedeai.ai and github.com/JasonColapietro. These are informational links to the vendor's official resources and do not involve automated network operations or remote code execution.

suede-paywalls