Third-party audit

Gen Agent Trust Hub

dpa-review · anthropics/claude-for-legal

Passed
Provider summary

This skill facilitates the review of Data Processing Agreements (DPAs) against a legal playbook and includes security considerations related to processing external documents. It primarily involves an indirect prompt injection surface when handling untrusted user-provided DPAs, which is common for document-analysis tools. The skill also interacts with local configuration paths to manage its legal playbooks and outputs. These behaviors are aligned with the skill's intended legal use case.

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

Provider
Gen Agent Trust Hub
Normalized result
pass
Risk level
NONE
Audited
Sep 14, 2026
Interpretation

How to use this signal

01

Confirm the source

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

02

Read the content

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

03

Limit permissions

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