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.onEventand RPC responses viahost.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