create-agent
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill interacts with the official Bolna API (api.bolna.ai) for agent creation and management, which is a verified vendor resource.
- [SAFE]: Credential management follows security best practices by utilizing environment variables for the BOLNA_API_KEY instead of hardcoded secrets.
- [COMMAND_EXECUTION]: Includes a Python utility (scripts/create_minimal_agent.py) for automating API interaction. The script uses standard libraries and performs safe argument parsing.
- [EXTERNAL_DOWNLOADS]: Configures agents to interface with well-known third-party services such as OpenAI (api.openai.com) for language processing.
- [INDIRECT_PROMPT_INJECTION]: The skill enables the creation of agents that ingest untrusted audio data. While this creates a potential surface for indirect prompt injection, it is the core functionality of the skill, and documentation provides guidance on using prompt placeholders as basic boundaries.
Audit Metadata