Gen Agent Trust Hub

policy-redraft · anthropics/claude-for-legal

Passed

Provider summary

This skill facilitates the redrafting of legal policies by identifying gaps and proposing revisions. It includes security considerations related to the processing of external regulatory and policy text, which serves as a surface for indirect prompt injection. The skill incorporates multiple guardrails, such as specific file path scoping, mandatory verification tagging, and the use of dedicated proposal files to prevent unintended modifications to source documents.

The provider classified the analyzed snapshot as NONE risk. This result applies to the content available at audit time.

Interpretation

Compare the repository, publisher, and installation command before continuing.

Review SKILL.md, scripts, and allowed tools. Artificial Atlas never executes them during indexing.

Use the narrowest possible scope and avoid broad credentials for third-party skills.