The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill provides a structured workflow that encourages the agent to request and analyze external data provided by the user, which could contain malicious instructions designed to influence the agent's behavior.
Ingestion points: SKILL.md (Step 1) and references/full.md (§9) instruct the agent to request game links, analytics dashboard screenshots/exports, and community feedback.
Boundary markers: The skill does not provide instructions to wrap external content in delimiters or to ignore embedded natural language instructions within the data.
Capability inventory: The skill itself contains no executable code, scripts, or automated tool definitions.
Sanitization: There are no specific instructions for the agent to sanitize or validate the external data before processing.
[NO_CODE]: The skill package consists entirely of Markdown documentation and reference materials. No Python, Node.js, or Shell scripts are included, which eliminates risk vectors associated with direct code execution, malicious dependencies, or obfuscated scripts.
[SAFE]: References to external domains like create.roblox.com and devforum.roblox.com point to official Roblox documentation. Other references, such as qptr.io and creatorexchange.io, are documented neutrally as niche developer tools and research aids consistent with the skill's purpose.

roblox-growth-design