visual-plan
Pass
Audited by Gen Agent Trust Hub on Jul 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
npx @agent-native/coreto install and run its core functionality. This involves downloading the latest version of the vendor's CLI tool from the npm registry at runtime. - [REMOTE_CODE_EXECUTION]: The skill executes remote code by utilizing
npxto run CLI commands for setup, connectivity management, and local plan operations. - [COMMAND_EXECUTION]: The skill relies on shell commands for operational tasks such as connecting to the hosted service, verifying local plan files (
plan local verify), and serving interactive previews (plan local serve). - [DATA_EXFILTRATION]: The skill is designed to send plan content, which may include code snippets and architecture details, to a hosted service at
https://plan.agent-native.com. A 'Local-Files Privacy Mode' is documented as an alternative to ensure data remains on the local filesystem. - [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection when importing existing plans or processing feedback from external sources, as it lacks explicit instructions for sanitizing these inputs before incorporating them into new plans.
Audit Metadata