openclaw-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 fetches and synthesizes content from public OpenClaw documentation (https://docs.openclaw.ai) and GitHub (https://github.com/openclaw/openclaw, raw.githubusercontent.com) and explicitly instructs the agent to read GitHub Issues/Discussions (user‑generated) as part of troubleshooting, so it clearly ingests untrusted third‑party content that could carry indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:31 PM