tools-unity-sentry
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill describes patterns for ingesting external data (e.g., user input, player state, monetization details) into diagnostic logs and breadcrumbs. This represents a potential indirect prompt injection surface if the logs are later processed by another agent, although no exploitable capabilities are present in the skill itself. 1. Ingestion points: inputData, playerState, productId, and userId fields in SKILL.md code snippets. 2. Boundary markers: None present. 3. Capability inventory: The skill snippets only interact with the Sentry SDK and do not include high-risk capabilities like file writing or subprocess execution. 4. Sanitization: Not explicitly shown in the instrumentation examples.
- [EXTERNAL_DOWNLOADS]: The skill references the official Sentry Unity SDK (io.sentry.unity) for installation via the Unity Package Manager. This is a reference to an official library from a well-known service provider.
- [COMMAND_EXECUTION]: Documents the use of sentry-cli for uploading debug symbols, which is a standard part of the build and deployment process for Unity games using Sentry.
Audit Metadata