advai-cli-unified-terminal-ai
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill facilitates downloading the
advai-clipackage from PyPI, npm, and Homebrew. It also includes commands to install additional skill sets and CLIs from GitHub repositories. - [COMMAND_EXECUTION]: The CLI tool manages local files in the
~/.advai/directory and can synchronize agent settings to platform-specific directories (e.g.,~/.cursor/skills/). It also acts as a proxy for executing third-party command-line utilities. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted content from remote repositories and local documents, which are then integrated into the AI agent's context.
- Ingestion points: Commands such as
advai skill install <URL>andadvai kb doc add <path>allow the ingestion of external code and text. - Boundary markers: The documentation does not specify the use of delimiters or warnings to prevent the agent from executing instructions embedded within ingested skills or documents.
- Capability inventory: The skill possesses the capability to write to the filesystem, perform network requests to download packages, and execute shell commands.
- Sanitization: No sanitization or validation logic is described for checking the integrity of downloaded skill definitions.
Audit Metadata