The Agent Skills Directory

[SAFE]: The skill uses standard HTML, CSS, and localized JavaScript for UI navigation. No external dependencies, network requests, or obfuscated code patterns were detected.
[SAFE]: The project includes a security checklist (references/checklist.md) that explicitly prohibits the use of sensitive browser APIs like localStorage and alert, demonstrating best practices for sandbox safety.
[PROMPT_INJECTION]: The skill consumes user-provided text to populate slide templates and outputs the result using the file_write capability. It does not provide the agent with specific instructions to escape or sanitize this content, which creates a potential surface for indirect prompt injection.
Ingestion points: User-provided headlines and body text processed by the agent.
Boundary markers: Not present in the instruction set for data interpolation.
Capability inventory: The skill uses the file_write capability to generate the output HTML artifacts (referenced in SKILL.md).
Sanitization: Absent; there are no instructions to validate or sanitize user input before it is written into the HTML structure.

editorial-burgundy-principles-template