confluence
Pass
Audited by Gen Agent Trust Hub on Apr 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill utilizes the vendor's official CLI tool (
@membranehq/cli) for all operations. - [SAFE]: Implements secure credential management by delegating authentication to the Membrane platform, ensuring that sensitive tokens are not handled directly by the agent or stored locally.
- [SAFE]: Encourages security best practices by explicitly instructing the agent not to request API keys from users.
- [SAFE]: All external interactions are scoped to the Confluence API and the vendor's infrastructure.
- [SAFE]: This skill possesses an indirect prompt injection surface as it ingests data from Confluence pages and blog posts, but it does not contain malicious instructions and adheres to safety guidelines by using a managed connection provider.
Audit Metadata