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 terminal tool, specifically hermes config set display.skin <name> and hermes 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 into write_file operations. 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
Risk Level
SAFE
Analyzed
Aug 14, 2026, 07:55 AM
Security Audit — agent-trust-hub — hermes-themes