✓
Third-party audit

Gen Agent Trust Hub

web-search · qu-skills/superpowers

Passed
Provider summary

This skill provides an interface for web searching and content extraction using the Tavily and Exa services via the inference.sh CLI. While it is functional and uses restricted tool permissions, it introduces a surface for indirect prompt injection by processing untrusted data from the web and passing it to an LLM.

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 02, 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. OpenAI Suite never executes them during indexing.

03

Limit permissions

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