Skills
Navigate
skills/jeremylongshore/tons-of-skills-marketplace/twinmind-enterprise-rbac/Gen Agent Trust Hub

twinmind-enterprise-rbac

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to manage and process meeting transcripts and summaries. This ingested data from external sources (meeting participants/audio) could contain malicious instructions designed to influence the agent's behavior during processing.
  • [COMMAND_EXECUTION]: The skill requests Bash access with npm and curl scopes to perform API verification and manage enterprise configurations.
  • [EXTERNAL_DOWNLOADS]: The skill uses curl to interact with the official TwinMind API (https://api.twinmind.com) for team member verification and setup validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 03:49 AM