shiny-ble-hosting
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: No attempts to override agent behavior or bypass safety guidelines were found. The instructions focus strictly on library usage and code generation conventions.
- [DATA_EXFILTRATION]: No sensitive file access or unauthorized network operations were detected. The skill handles local BLE interactions as intended by the library's purpose.
- [REMOTE_CODE_EXECUTION]: No remote code execution patterns or unsafe package installations were identified. The mentioned NuGet package is a standard community library for the specified functionality.
- [INDIRECT_PROMPT_INJECTION]: The skill documents APIs that ingest untrusted data from BLE central devices (e.g., via
WriteRequest.Data). While this creates an attack surface typical for BLE applications, the skill does not suggest unsafe processing of this data (such as direct interpolation into prompts or shell commands). - [OBFUSCATION]: No hidden or encoded content (Base64, zero-width characters, or homoglyphs) was detected in the provided files.
Audit Metadata