NYC

talos-os-expert

Warn

Audited by Snyk on Feb 15, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The skill repeatedly instructs fetching and applying content from public third‑party URLs (e.g., wget/curl of GitHub releases and raw.githubusercontent.com, ghcr.io images, and curl | sh from talos.dev), which are untrusted/user-generated sources and are consumed as part of the workflow.

MEDIUM W013: Attempt to modify system services in skill instructions.

  • Attempt to modify system services in skill instructions detected (high risk: 1.00). This skill contains explicit, high-risk operational instructions (talosctl apply-config, disk wipe/encryption, writing files under /etc, bootstrap/reset/reboot commands, installer scripts) that modify system state and can destructively change or erase machines, so it should be flagged.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:32 PM