chaport

Pass

Audited by Gen Agent Trust Hub on May 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Membrane CLI (membrane) to perform actions such as searching for connectors, managing connections, and executing API requests. These commands are standard for the skill's intended purpose of managing Chaport data.
  • [EXTERNAL_DOWNLOADS]: The instructions recommend the global installation of the @membranehq/cli package via NPM. This is a trusted resource provided by the skill's author to enable the integration's functionality.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it processes untrusted data from an external source.
  • Ingestion points: Untrusted data enters the agent context from Chaport via commands like membrane action run list-visitors and membrane action run list-chat-events (SKILL.md).
  • Boundary markers: The instructions do not define specific markers to delimit external data from agent instructions.
  • Capability inventory: The skill includes the ability to perform write and delete operations, such as send-message, update-visitor, and delete-visitor (SKILL.md).
  • Sanitization: There are no documented sanitization or validation steps for data retrieved from the Chaport API.
Audit Metadata
Risk Level
SAFE
Analyzed
May 3, 2026, 06:04 PM
Security Audit — agent-trust-hub — chaport