The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests content from external documentation pages at create.roblox.com. While this is a trusted official source, reading external content represents a standard ingestion surface for indirect instructions.
Ingestion points: Remote markdown and text content fetched via the http_get tool from create.roblox.com as defined in SKILL.md and references/lookup-patterns.md.
Boundary markers: The skill does not define specific delimiters to wrap or isolate the fetched documentation content from the agent's instructions.
Capability inventory: The skill is scoped to information retrieval and documentation lookups; it does not request file-system write access or arbitrary command execution.
Sanitization: No specific content sanitization or filtering is described for the fetched documentation data.
[SAFE]: The skill performs read-only documentation lookups from official Roblox domains. It follows a structured workflow to verify API details and requires citations for its claims, ensuring transparency and reliability. No malicious code, obfuscation, or unauthorized data access patterns were identified.

roblox-docs