Back to plugin

Security audit

MoltGuard

Security checks for vulnerabilities and agentic risk

Overview

Prompt-injection indicators were detected in the submitted artifacts (ignore-previous-instructions, system-prompt-override, unicode-control-chars); human review is required before treating this skill as clean.

Install MoltGuard only if you want a security gateway with broad visibility into OpenClaw activity. After installing, review the local gateway setting, Core API URL, API key handling, autoscan setting, and dashboard logs, especially before using it with confidential workspaces. ClawScan detected prompt-injection indicators (ignore-previous-instructions, system-prompt-override, unicode-control-chars), so this skill requires review even though the model response was benign.

SkillSpector was not run because this plugin release contains no bundled skills.

Endor dependency reachability

Checked Nov 10, 2026 · 3:27 PM UTC

2 reachable vulnerabilities

  • Medium

    undici vulnerable to Denial of Service via unhandled exception in cache-interceptor response replay

    undici@8.10.2Fixed in 8.12.4

    CVE-2026-1202222 packages import undici@8.10.2 directly. See the list of all dependency paths for details.
  • High

    undici vulnerable to TLS certificate validation bypass via dropped tls options in Agent

    undici@8.10.2Fixed in 8.12.2

    GHSA-2m5v-pch6-74hx2 packages import undici@8.10.2 directly. See the list of all dependency paths for details.