The Agent Skills Directory

[SAFE]: The skill is purely instructional and does not contain any executable scripts or binary files. It consists of markdown documentation meant to guide an AI agent's analysis process.
[SAFE]: No external network operations, data exfiltration patterns, or hardcoded credentials were detected. All URL references are absent, and the skill does not request access to sensitive local files.
[SAFE]: The skill does not include any obfuscation, persistence mechanisms, or privilege escalation commands. The C# code provided is a static example for documentation purposes and is not executed by the agent environment.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data (AI-generated Unity code). However, since the skill has no exploitable capabilities such as file writing, network access, or shell execution, and only generates text-based reviews, the risk is classified as safe.
Ingestion points: Processes user-provided 'Render Graph renderer feature code' as defined in SKILL.md.
Boundary markers: None explicitly defined for the untrusted input.
Capability inventory: No subprocess calls, file-write operations, or network requests are present in the skill.
Sanitization: No explicit sanitization or filtering of the input code is described, but the output is restricted to technical validation text.

validate-urp-render-graph-renderer-feature