bluesky-by-unshape

Pass

Audited by Gen Agent Trust Hub on May 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @membranehq/cli package from the public npm registry. This is an expected procedure for utilizing the vendor's integration tooling.
  • [COMMAND_EXECUTION]: The skill relies on executing membrane CLI commands to perform authentication, discover actions, and execute logic. These commands are scoped to the functionality of the Membrane platform.
  • [SAFE]: The skill adheres to secure identity management practices by utilizing an OAuth-like flow (membrane login) and advising the agent never to request or store raw API keys locally, leveraging server-side credential management instead.
Audit Metadata
Risk Level
SAFE
Analyzed
May 2, 2026, 08:18 PM
Security Audit — agent-trust-hub — bluesky-by-unshape