Skills
Navigate
skills/sirkirby/unifi-mcp/unifi-access-setup/Gen Agent Trust Hub

unifi-access-setup

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute local setup and prerequisite scripts (check-prereqs.sh, set-env.sh) located within the plugin directory.
  • [PRIVILEGE_ESCALATION]: On Windows systems, the skill uses powershell -ExecutionPolicy Bypass to execute its prerequisite and environment configuration scripts.
  • [INDIRECT_PROMPT_INJECTION]: The skill reads and migrates configuration data from local environment files and project-level settings.
  • Ingestion points: Accesses configuration data from ~/.config/unifi-mcp/access.env and .claude/settings.local.json (SKILL.md).
  • Boundary markers: Recommends that the agent only display a sanitized summary of existing configurations to the user instead of raw data.
  • Capability inventory: Utilizes Bash for configuration updates and Read for inspecting existing settings.
  • Sanitization: The instructions explicitly direct the agent to sanitize host summaries and variable names to prevent the exposure of stored credentials during the interaction.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 08:16 PM