Confirm the source
Compare the repository, publisher, and installation command before continuing.
×
Third-party audit
High riskGen Agent Trust Hub
notion-meeting-intelligence · openai/skills
Provider summary
The skill is highly vulnerable to indirect prompt injection because it ingests untrusted data from Notion pages and has the capability to write back to the workspace without sanitization or boundary markers. It also relies on an external, unverified MCP tool for its core functionality.
The provider classified the analyzed snapshot as HIGH risk. This result applies to the content available at audit time.
- Provider
- Gen Agent Trust Hub
- Normalized result
- fail
- Risk level
- HIGH
- Audited
- Feb 15, 2026
How to use this signal
Read the content
Review SKILL.md, scripts, and allowed tools. OpenAI Suite never executes them during indexing.
Limit permissions
Use the narrowest possible scope and avoid broad credentials for third-party skills.