hermes-themes
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions guide the agent to perform shell operations via the
terminaltool, specificallyhermes config set display.skin <name>andhermes skin set <key> <hex>. These commands directly incorporate user-provided parameters, creating a potential command injection surface if a user provides a name or hex code containing shell metacharacters (e.g.,;,&&,|). - [PROMPT_INJECTION]: The skill uses an indirect injection surface by reading external skin files (
read_file,search_files) and incorporating user-supplied values intowrite_fileoperations. Maliciously crafted skin files or user inputs could potentially influence agent behavior if they contain instructions disguised as theme metadata or labels. - [DATA_EXPOSURE]: The skill is designed to read and write files within the application's configuration directory (
~/.hermes). While legitimate for its purpose, it requires the agent to handle local configuration data that could be sensitive depending on the user's environment.
Audit Metadata