repo-orchestration
Pass
Audited by Gen Agent Trust Hub on Aug 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed for repository orchestration, focusing on the creation of design artifacts (ADRs, Design Docs) and task ledgers based on existing architecture analysis. It contains no instructions that attempt to bypass AI safety guidelines or exfiltrate data.
- [DATA_EXPOSURE]: The skill does not access sensitive user credentials, environment variables, or private configuration files. Its operations are limited to reading provided architecture artifacts and writing documentation to the
.reposkillopt/directory. - [COMMAND_EXECUTION]: The skill explicitly defines itself as a design tool that produces a portable plan as an artifact rather than an executor. It states that it never executes the implementation plan it generates, mitigating risks associated with unauthorized shell operations.
- [REMOTE_CODE_EXECUTION]: There are no remote downloads or external script executions. While the CHANGELOG mentions a local engine script (
reposkillopt_engine/artifact_checks.py), it is described as a deterministic check for artifact consistency and is part of the vendor's internal tooling.
Audit Metadata