toolkit
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides tools for the agent to ingest and process untrusted external data through AI services, creating an attack surface for indirect prompt injection instructions. * Ingestion points: Untrusted data enters the agent context via
AIClient.generate_text,AIClient.summarize, andAIClient.text_to_sqlcalls documented inSKILL.md. * Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the documentation to isolate untrusted content. * Capability inventory: The skill provides a wide range of powerful capabilities acrossSKILL.md, including arbitrary SQL execution (SqlClient), file management (FileClient), and user/group administration (UserClient/GroupClient). * Sanitization: The provided implementation patterns do not include sanitization or validation of external content before it is interpolated into AI prompts. - [EXTERNAL_DOWNLOADS]: The skill instructions include downloading the
@domoinc/toolkitpackage from the public NPM registry, which is the official library for interacting with well-known Domo platform services.
Audit Metadata