skills/shinyorg/skills/shiny-core/Gen Agent Trust Hub

shiny-core

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides technical documentation for a legitimate software development framework. The infrastructure, hosting models, and platform abstractions described are standard for cross-platform .NET applications.
  • [INDIRECT_PROMPT_INJECTION]: The skill documents a framework that facilitates data ingestion, creating a theoretical surface for indirect injection as part of its standard operation.
  • Ingestion points: Data is ingested through IKeyValueStore, IRepository, and IRemoteConfigurationProvider as described in SKILL.md and reference/api-reference.md.
  • Boundary markers: Explicit delimiters or boundary markers for untrusted input are not defined in the provided framework instructions.
  • Capability inventory: The framework includes capabilities for file system access (IRepository, IPlatform) and network configuration (AddRemote).
  • Sanitization: No specific sanitization or validation mechanisms for ingested data are detailed in the documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 11:41 PM
Security Audit — agent-trust-hub — shiny-core