Skill Antivirus & Security Scanner

ReviewAudited by ClawScan on May 10, 2026.

Overview

MoltGuard has a coherent security purpose, but this reviewed skill mainly tells the agent to install an external unreviewed plugin and use a Core service that may handle sensitive content.

Install only if you trust the MoltGuard package and Core service. Before enabling it, verify the source/version, require explicit approval for installation, understand what data is sent to Core, and protect any generated API key.

Findings (3)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

The agent could install and run a separate plugin whose code and exact version were not reviewed here.

Why it was flagged

The reviewed package is instruction-only but directs installation of an external, unpinned plugin package, shifting the real behavior to code not present in the supplied artifacts.

Skill content
When the human asks to install MoltGuard, or when you want to protect yourself: ... openclaw plugins install @openguardrails/moltguard
Recommendation

Require explicit human approval, verify the package source, and pin or inspect the trusted version before installing.

What this means

Prompts, commands, file-derived content, or secret/PII-related material may be processed by an external Core service.

Why it was flagged

The skill discloses external Core-based detection over sensitive risk surfaces, but it does not specify exact payloads, filtering, retention, or user approval boundaries.

Skill content
All security detection is performed by Core: ... Data Risk — Secret leakage, PII exposure, sending sensitive data to LLMs
Recommendation

Review Core privacy and retention terms, use an enterprise/private Core if needed, and avoid enabling it for sensitive environments without clear data-handling controls.

What this means

The MoltGuard API key and agent ID may appear in local files or agent output/logs if displayed.

Why it was flagged

The skill uses MoltGuard account/agent credentials for quota and claiming, and the instructions say those credentials are stored locally and can be displayed.

Skill content
Get your API key from Core; Credentials saved to `~/.openclaw/credentials/moltguard/` ... `/og_status` Shows your API key
Recommendation

Treat the MoltGuard API key as a secret, avoid pasting it into untrusted places, and rotate it if exposed.