NYC

openclaw-config

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: 1.00). The skill explicitly installs and loads external skills from ClawdHub/GitHub (clawdhub install, npx add-skill) and lists social/web plugins like bird (X/Twitter), blogwatcher and web search (Brave Search), which means the agent will fetch and ingest untrusted, user-generated public web/social content into its runtime context.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:10 PM