teamsupport

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The instructions direct the user to install the @membranehq/cli package from the npm registry, which is the official tool provided by the vendor.
  • [COMMAND_EXECUTION]: The skill operates through the execution of membrane CLI commands for authentication, service connection, and action management.
  • [DATA_EXFILTRATION]: The skill transmits data between the local environment, the TeamSupport API, and the Membrane platform (getmembrane.com) as part of its documented functionality.
  • [PROMPT_INJECTION]: There is a potential for indirect prompt injection because the skill retrieves and processes user-generated content (e.g., tickets, KB articles) from TeamSupport. This content could be crafted to influence the agent's behavior.
  • Ingestion points: Data returned from the execution of actions via membrane action run (SKILL.md).
  • Boundary markers: No specific delimiters or warnings for the agent to ignore instructions within the retrieved data are present.
  • Capability inventory: The agent can execute commands and run arbitrary actions, providing a surface for misuse if an injection is successful.
  • Sanitization: The instructions do not specify any validation or sanitization steps for data retrieved from TeamSupport.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 11:51 PM
Security Audit — agent-trust-hub — teamsupport