anygen-diagram
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill initiates the installation of the
@anygen/cliNode.js package as specified in the metadata frontmatter. This package is the primary tool for executing the skill's logic. - [COMMAND_EXECUTION]: The skill instructions include commands for user authentication (
anygen auth login) and the installation of secondary skills (anygen skill install). These operations involve executing shell commands on the host system. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to take user-supplied text (diagram descriptions, mind maps) and process it via the AnyGen CLI, creating a surface for potential injection.
- Ingestion points: User-provided textual descriptions of diagrams, architecture, or flowcharts in the request.
- Boundary markers: None explicitly defined in the prompt instructions to separate user content from command arguments.
- Capability inventory: The skill has the capability to execute shell commands (
anygen) and install additional software packages. - Sanitization: No specific sanitization or validation logic for the user-supplied strings is documented.
Audit Metadata