creative-media
Pass
Audited by Gen Agent Trust Hub on Aug 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads the
luxin-clipackage from the npm registry using thenpxcommand. - [REMOTE_CODE_EXECUTION]: Executing
npx -y luxin-cli@latestresults in the automatic download and execution of the latest version of the vendor's code from a remote registry. - [COMMAND_EXECUTION]: The instructions contain several shell commands intended for the agent to execute to interact with the media service, including configuration, media creation, and environment variable management.
- [PROMPT_INJECTION]: The skill workflow involves executing commands suggested by the CLI output (e.g.,
data.next_command). This represents a surface for indirect prompt injection where tool output influences subsequent agent actions. Ingestion points include the--promptargument and the dynamic command responses; no explicit boundary markers or sanitization steps for this untrusted data are documented in the skill file.
Audit Metadata