hermes-desktop-plugins

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the AI to write JavaScript ESM files to the local filesystem, typically at ~/.hermes/desktop-plugins/, which are then dynamically loaded and executed by the Hermes desktop application.
  • [DATA_EXFILTRATION]: The provided SDK allows plugins to access internal application state atoms and perform JSON-RPC requests to the Hermes gateway, creating a pathway for accessing and potentially moving sensitive application data.
  • [PROMPT_INJECTION]: The skill facilitates indirect prompt injection by allowing plugins to ingest and display data from external gateway events and API responses. 1. Ingestion points: Gateway events via host.onEvent and RPC responses via host.request. 2. Boundary markers: No delimiters or ignore instructions are specified for external data. 3. Capability inventory: UI registration, gateway commands, and navigation. 4. Sanitization: No explicit requirements for sanitizing external content before rendering are provided.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 07:56 AM
Security Audit — agent-trust-hub — hermes-desktop-plugins