horde
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill automates the configuration of well-known and legitimate Elixir packages from the official Hex registry.
- [SAFE]: The generated Elixir code follows security best practices, including a HordeSupervisor with a module allowlist and a ClusterMonitor that validates node membership using trusted suffixes.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface as part of its core functionality. 1. Ingestion points: Reads local project files including mix.exs, application.ex, and individual GenServer modules to extract application metadata and structure. 2. Boundary markers: Absent. 3. Capability inventory: File system read and write access, and execution of the mix deps.get command. 4. Sanitization: Absent. The risk is assessed as safe because the file ingestion is restricted to standard project files required for the skill's primary purpose of code generation and configuration.
Audit Metadata