Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

Flow State Monitoring

v1.0.0

Workflow-driven skill that infers deep focus and autonomously mutes interruptions.

0· 26·1 current·1 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for zvirb/flow-state-monitoring.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Flow State Monitoring" (zvirb/flow-state-monitoring) from ClawHub.
Skill page: https://clawhub.ai/zvirb/flow-state-monitoring
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Canonical install target

openclaw skills install zvirb/flow-state-monitoring

ClawHub CLI

Package manager switcher

npx clawhub@latest install flow-state-monitoring
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Suspicious
medium confidence
!
Purpose & Capability
The skill's stated purpose is to create calendar entries in Google Workspace, but it declares no required credentials, API keys, or permissions. Creating calendar events normally requires OAuth/API credentials (or a separate authorized skill). The absence of any declared Google Workspace auth is a mismatch with the claimed capability.
!
Instruction Scope
SKILL.md instructs: WHEN [telemetry from local sensors indicates deep focus] THEN run sub-agents llm_classify_intent and gworkspace_calendar_create. It does not specify what 'local sensors' are, how telemetry is read, or which files/APIs to use — leaving broad discretion to access microphones, system activity, or other sensors. It also delegates calendar writes to another capability without defining required auth or safe-guards.
Install Mechanism
Instruction-only skill with no install steps and no code files. This minimizes direct disk installation risk; the scanner had no files to analyze.
!
Credentials
No environment variables or credentials are declared despite the skill's need to modify Google Workspace calendar state. That omission is disproportionate — either the skill expects credentials to come from elsewhere (other skills or global agent config) or the manifest is incomplete/misleading.
!
Persistence & Privilege
The skill allows autonomous invocation (platform default). Autonomous execution combined with vague instructions to read 'local sensors' and to update calendar entries increases the potential impact. While 'always' is false (good), the skill's autonomy plus unclear sensor/data access is a risk if deployed without permissions controls.
What to consider before installing
This skill's behavior is ambiguous and asks the agent to bridge two sensitive domains: local sensor telemetry and calendar control. Before installing, ask the publisher for: (1) explicit list of what 'local sensors' are accessed and how (e.g., microphone, OS activity, installed apps) and what data is collected/stored; (2) the exact authorization flow for Google Workspace (OAuth scopes, whether user consent is required, or whether it expects pre-provisioned service account keys); (3) the identities and implementations of the referenced sub-agents (llm_classify_intent and gworkspace_calendar_create) and whether they are already installed/authorized; (4) logging, data-retention, and opt-out controls. If you proceed, prefer: manual invocation rather than autonomous runs; least-privileged OAuth scopes limited to calendar writes; testing in a sandbox account; and revocable, time-bound credentials. Because the manifest omits these details, treat it as suspicious until the author provides clarifying documentation or a source repository.

Like a lobster shell, security has layers — review code before you run it.

latestvk978adg3hvjxfwz72zjz67xrgx85kg18
26downloads
0stars
1versions
Updated 4h ago
v1.0.0
MIT-0

Lean Philosophy (Principles)

  • Kaizen (改善): This skill is an atomic node, broken down into its simplest, smallest component to eliminate waste and ensure perfection.
  • Standardized Work (Hyojun Sagyo): This node represents the most efficient, standardized path for this specific task before automation.
  • Jidoka (自働化): This node includes autonomous defect detection. It will stop immediately and report if it cannot achieve the expected outcome.

Flow State Monitoring

This skill orchestrates a workflow to analyze focus telemetry and autonomously update your status in Google Workspace to protect your flow state.

Cognitive Directives

WHEN [telemetry from local sensors indicates deep focus] THEN [Execute llm_classify_intent (Sub-Agent) to classify the activity. If classified as "Deep Work", Execute gworkspace_calendar_create with schema: { "summary": "Busy - In Flow", "status": "busy" } to block interruptions]

Expected Output

A JSON confirmation of the calendar status update.

Comments

Loading comments...