Gen Agent Trust Hub

brand-style · anthropics/knowledge-work-plugins

Passed

Provider summary

This skill manages brand look and output preferences by researching user-provided website links or descriptions. It presents a potential surface for indirect prompt injection when processing external website metadata, which is a standard consideration for web-enabled skills. While these features are core to the skill's functionality, they involve interacting with untrusted third-party content.

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. OpenAI Suite never executes them during indexing.

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