ClawHub
Back to skill

Security audit

Simple Random Interaction Designer

Security checks for vulnerabilities and agentic risk

Overview

This skill is not destructive, but it enables automated proactive messages that may use personal context without clear consent, rate limits, or transparency.

Install only if you want OpenClaw to make spontaneous check-ins and your OpenClaw setup separately enforces opt-in, data-source permissions, quiet hours, and rate limits. Be especially cautious if calendar, smart-home, traffic, or other personal integrations are enabled.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly enables proactive outreach and, in some interaction categories, instructs the agent to use accessible user/context data such as calendar, weather, smart-home, traffic, news, or market context. Although it cautions against fabrication, it does not require an explicit user-facing consent or transparency mechanism before initiating privacy-sensitive, data-aware messages, which can lead to covert profiling or unexpected use of personal data.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The instruction not to mention the random process, scheduled checks, or why the interaction was selected intentionally suppresses transparency about automated proactive messaging. In the context of unsolicited outreach, hiding that the message was system-initiated can mislead users about why they were contacted and obscure the role of automation and contextual data usage.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The script is explicitly designed to trigger unsolicited, human-like outreach during periodic checks, but it contains no mechanism for user consent, visibility, rate limiting, or contextual safety controls. In an agent setting, this can cause deceptive or unwanted contact, erode user trust, and create privacy or compliance issues if proactive messages are sent without clear opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.