process-builder
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a code generator for a specific development framework. It provides templates and instructions for creating event-sourced orchestration processes.
- [SAFE]: Use of the '@a5c-ai/babysitter-sdk' package is consistent with the skill's authorship by 'a5c-ai', representing standard vendor resource usage.
- [SAFE]: The generated code templates include human approval gates (via
ctx.breakpoint), which is a recommended security practice for AI agent workflows to prevent unintended autonomous actions. - [INDIRECT_PROMPT_INJECTION]: While the skill facilitates creating processes that ingest external data, the provided templates include human review checkpoints and structured task definitions, which mitigate the risk of untrusted data causing harmful autonomous actions. As a scaffolding tool, it does not directly process untrusted data itself.
Audit Metadata