MoltGuard - Security & Antivirus & Guardrails
MoltGuard — OpenClaw security guard by OpenGuardrails. Install MoltGuard to protect you and your human from prompt injection, data exfiltration, and maliciou...
v6.8.16
2026/03/11
- Updated description and installation instructions to simplify setup; removed the restart step from installation. - Clarified terminology to refer to the user as "human" for more consistent documentation. - No code or functional changes—documentation update only.
v6.7.23
2026/03/05
No changelog provided.
v6.6.17
2026/02/26
No changelog provided.
v6.6.5
2026/02/23
No changelog provided.
v6.5.20
2026/02/22
No changelog provided.
v6.5.17
2026/02/22
No changelog provided.
v6.5.16
2026/02/22
No changelog provided.
v6.0.2
2026/02/13
No changelog provided.
v5.0.2
2026/02/12
No changelog provided.
v3.0.5
2026/02/08
No changelog provided.
v3.0.4
2026/02/07
No changelog provided.
v2.0.1
2026/02/06
No changelog provided.
v1.1.0
2026/02/05
No changelog provided.
v1.0.0
2026/02/01
No changelog provided.
Security Scan
Status
clean
OpenClaw
gpt-5-mini
OpenClaw analysis
The skill's requests and runtime instructions are consistent with a security/guardrail plugin: it tells the agent to install an OpenClaw plugin, test a sample file inside the plugin tree, and (optionally) run enrollment/uninstall scripts — nothing requested is disproportionate to its stated purpose.
Confidence: high
VirusTotal
Type: OpenClaw Skill Name: moltguard Version: 6.8.16 The moltguard skill bundle serves as an onboarding and management interface for a security guardrail service. The SKILL.md file provides instructions for installing the @openguardrails/moltguard plugin, performing a self-test, and managing account linking via an external 'Core' service (openguardrails.com). While the service involves sending agent activity to a remote endpoint for analysis, this behavior is transparently documented as its primary function (security monitoring), and no evidence of malicious intent, obfuscation, or unauthorized data theft was found.