eightctl

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses go install to download the eightctl utility from github.com/steipete/eightctl/cmd/eightctl@latest. This is an unversioned binary installation from a repository managed by an individual.
  • [COMMAND_EXECUTION]: The skill facilitates shell command execution via the eightctl binary to interact with Eight Sleep pod hardware, including status checks and temperature control.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from the Eight Sleep API via commands like eightctl status and eightctl alarm list (SKILL.md). It lacks explicit boundary markers or sanitization, creating an indirect prompt injection surface if pod-related metadata or alarm names were poisoned. The skill has the capability to execute further commands based on this context.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 08:32 AM
Security Audit — agent-trust-hub — eightctl