mailbluster

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill provides a legitimate integration with the Mailbluster API via the Membrane platform, emphasizing secure credential handling through managed connections.- [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the official vendor CLI tool (@membranehq/cli) from the public NPM registry.- [COMMAND_EXECUTION]: The skill utilizes the membrane CLI to perform operations such as authentication, connection management, and action execution.- [SAFE]: An indirect prompt injection surface exists where the skill accepts external data to be processed by Mailbluster actions.
  • Ingestion points: Data passed to the --input parameter in membrane action run (SKILL.md).
  • Boundary markers: None specified.
  • Capability inventory: API interaction and network communication via the membrane CLI (SKILL.md).
  • Sanitization: Not explicitly defined in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 08:42 PM