eightctl

Pass

Audited by Gen Agent Trust Hub on Feb 23, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill configuration defines an installation step that downloads source code from a third-party repository on GitHub (github.com/steipete/eightctl/cmd/eightctl).
  • [REMOTE_CODE_EXECUTION]: The installation process uses the Go toolchain to fetch and compile a binary from a remote source at runtime, which is an external dependency execution vector.
  • [COMMAND_EXECUTION]: The skill relies on executing the 'eightctl' binary to manage device states, schedules, and local configuration files stored in the user's home directory (~/.config/eightctl/).
  • [PROMPT_INJECTION]: The skill processes data returned from the Eight Sleep API, creating a surface for indirect prompt injection if the API provides untrusted or maliciously crafted content.
  • Ingestion points: Command outputs from 'eightctl status', 'alarm list', and 'schedule list' are ingested into the agent's context (SKILL.md).
  • Boundary markers: No specific delimiters or safety instructions are provided to the agent to differentiate between the tool's output and its internal logic.
  • Capability inventory: The skill has the capability to run system commands ('eightctl') and perform network requests to external APIs (SKILL.md).
  • Sanitization: There is no indication of sanitization, filtering, or validation of the data retrieved from the Eight Sleep service before it is presented to the LLM.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 23, 2026, 12:56 PM