The Agent Skills Directory

[NO_CODE]: The skill consists entirely of Markdown-formatted templates, guides, and reference documents. There are no scripts, binaries, or configuration files that trigger code execution.
[SAFE]: No malicious patterns, such as prompt injection, credential harvesting, or data exfiltration attempts, were detected. The skill operates exclusively as a text-generation assistant for strategic documentation.
[INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing user-supplied product data to generate narratives.
Ingestion points: Clarification prompts in SKILL.md and input fields in templates within the assets/ directory (e.g., vision_board_template.md).
Boundary markers: The skill uses standard Markdown structural elements (headers, blockquotes) to separate instructions from generated content.
Capability inventory: There are no shell commands, network requests, or file system modifications identified in any file, including SKILL.md, assets/, references/, or examples/.
Sanitization: No explicit input validation or escaping is performed as the skill's output is intended for static human-readable documentation.

product-vision