openclaw-extend

Warn

Audited by Snyk on Feb 16, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The skill explicitly integrates public messaging channels (references/channel-setup.md lists WhatsApp, Telegram, Discord, Matrix where arbitrary users can send messages) and also allows installing plugins/hooks from npm or arbitrary archive URLs (references/plugin-hook-authoring.md), so it ingests untrusted user-generated third‑party content as part of its workflow.

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

  • Attempt to modify system services in skill instructions detected (high risk: 0.80). The skill instructs installing/uninstalling node hosts "as system service" and restarting daemons (and other system-level operations), which imply modifying system service files and requiring elevated privileges that can change the machine state.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 03:14 AM