openserv-multi-agent-workflows
Pass
Audited by Gen Agent Trust Hub on Jul 23, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill uses instructional warnings like 'CRITICAL' and 'IMPORTANT' to ensure users correctly define workflow edges and goals for successful platform validation. These are benign and intended for functional correctness.
- [DATA_EXPOSURE]: The examples demonstrate standard secret management by instructing users to use
.envfiles for private keys. Code snippets useprocess.envto access credentials securely, and all examples use placeholder values. - [EXTERNAL_DOWNLOADS]: The setup documentation references official platform packages and well-known libraries from the NPM registry. It also provides standard platform commands for updating skills from the project's official repository.
- [INDIRECT_PROMPT_INJECTION]: The workflow patterns involve passing data between agents using template interpolation (e.g.,
{{trigger.topic}}). While this creates a potential surface for indirect injection from external inputs, it is the primary intended functionality of the orchestration service and is not used maliciously here.
Audit Metadata