godot-code-review
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions and code examples for reviewing GDScript and C# code within the Godot engine. No suspicious patterns were detected across any threat categories.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted code snippets provided by the user. While this represents a theoretical attack surface for indirect prompt injection, the skill possesses no capabilities (such as network access, file system writes, or command execution) that could be exploited. The agent's output is limited to a textual code review summary, rendering the risk negligible.
- Ingestion points: User-provided code snippets referenced in the skill's triggers (e.g., "review this script").
- Boundary markers: None explicitly defined in the instructions.
- Capability inventory: No dangerous tools or commands are requested or used.
- Sanitization: None specified, but unnecessary given the lack of executable capabilities.
Audit Metadata