doany-website-builder
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to run the official DoAny CLI via
npx -y @doany-ai/cli, which fetches the package from the npm registry. - [COMMAND_EXECUTION]: The skill relies on executing local shell commands using the
doanyCLI tool to perform actions such as project creation, task management, and site publication. - [DYNAMIC_EXECUTION]: The use of
npxinvolves the dynamic downloading and execution of Node.js code from a remote registry at runtime. - [INDIRECT_PROMPT_INJECTION]: The skill allows the agent to ingest content from external websites to use as design references. This creates a surface where malicious instructions could be embedded in the reference site to influence the website-building task. * Ingestion points: External URLs provided as design references in SKILL.md. * Boundary markers: The instructions specify that external site content should be treated strictly as reference material. * Capability inventory: The skill has the ability to create companies, execute operations, and publish web applications via the DoAny platform. * Sanitization: There is no mention of explicit content filtering or sanitization of the external site data before it is processed by the agent.
Audit Metadata