wf-apps-migrate-lovable
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the agent to execute various shell commands to set up projects, generate components, and publish the application using the
daanddomoCLI tools. It also provides a Python one-liner to programmatically generate a required thumbnail asset using the Pillow library. - [EXTERNAL_DOWNLOADS]: The migration instructions recommend the installation of specific integration libraries from the Domo ecosystem, including
ryuu.jsand@domoincscoped packages for data querying and API interactions. - [PROMPT_INJECTION]: The core functionality of the skill involves an agent analyzing and modifying external application source code. This process creates an attack surface for indirect prompt injection, where malicious instructions could be embedded in the code being migrated to influence the agent's behavior.
- Ingestion points: External application source files (Next.js, Remix, etc.) that the agent is instructed to analyze and modify.
- Boundary markers: There are no specific delimiters or safety warnings provided to isolate the external code from the agent's control instructions.
- Capability inventory: The agent has access to shell command execution (
da,npm,domo,python3), file system modifications, and network-based deployment capabilities. - Sanitization: The skill does not include steps to sanitize or verify the integrity of the external source code before it is processed.
Audit Metadata