hermes-ide-terminal

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The installation guide includes the standard command to download and execute the Rust toolchain installer from sh.rustup.rs via shell piping.
  • [EXTERNAL_DOWNLOADS]: Recommends downloading pre-built binaries from the project's official website and installing the official @anthropic-ai/claude-cli package for authentication.
  • [COMMAND_EXECUTION]: Provides instructions for installing system dependencies using apt and building the project using npm and tauri commands.
  • [INDIRECT_PROMPT_INJECTION]: The skill details a project scanning mechanism in src-tauri/src/project/scanner.rs that parses files such as package.json and Cargo.toml to build context for AI agents.
  • Ingestion points: Project configuration files and directory structures analyzed during the scanning process mentioned in SKILL.md.
  • Boundary markers: The documentation does not explicitly detail the use of delimiters when providing this context to the agent.
  • Capability inventory: Terminal session management via PTY, file system access, and command execution capabilities.
  • Sanitization: The scanning logic extracts structural and dependency information without specific sanitization routines shown in the code snippets.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 06:50 PM
Security Audit — agent-trust-hub — hermes-ide-terminal