skills/elizaos/eliza/apple-reminders/Gen Agent Trust Hub

apple-reminders

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS] (LOW): The skill installs the remindctl binary from a third-party source (steipete/tap/remindctl via Homebrew or GitHub via pnpm). This source is not on the trusted organizations list, though it is the primary repository for the tool described.
  • [INDIRECT_PROMPT_INJECTION] (LOW): The skill processes reminder data which could contain malicious instructions meant to influence the agent.
  • Ingestion points: Command outputs from remindctl all, remindctl today, and remindctl list (SKILL.md).
  • Boundary markers: Absent; there are no instructions to the agent to treat reminder content as untrusted data or use delimiters.
  • Capability inventory: Subprocess execution via shell commands to interact with remindctl (SKILL.md).
  • Sanitization: Absent; the skill does not provide mechanisms to escape reminder titles or notes before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 06:11 PM