new-block
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run local development commands, specifically
poetry run pytestfor testing new blocks andpoetry run formatfor code styling. These are standard developer operations within the context of the AutoGPT Block SDK. - [SAFE]: No evidence of prompt injection, data exfiltration, or obfuscation was found. The skill's behavior and referenced file paths (e.g.,
backend/blocks/,docs/platform/block-sdk-guide.md) are consistent with its stated purpose of assisting in platform development.
Audit Metadata