The Agent Skills Directory

[SAFE]: The skill provides informational content and strategy frameworks for 'Engineering as Marketing'. No executable scripts, binary files, or system-level commands are included in the skill package.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided business descriptions and read local context files like .agents/product-marketing.md to provide tailored advice.
Ingestion points: User input prompts and the .agents/product-marketing.md context file.
Boundary markers: None explicitly defined within the skill instructions.
Capability inventory: No risky capabilities detected; the skill performs no subprocess calls, file writes, network operations, or dynamic code execution.
Sanitization: Standard LLM guardrails apply; no additional sanitization logic is implemented within the skill.
[SAFE]: No obfuscated content, Base64 strings, or hidden URLs were detected during the analysis. All references point to local documentation within the skill structure.

free-tools