Security audit

Openweruh

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent screen-monitoring assistant, but it includes background recording and activity tracking without clear retention limits or user controls.

Install only if you are comfortable with a skill inspecting active screen content and potentially recording observations for later summaries. Before using it, confirm how to disable it, whether silent mode is enabled, where summaries or observations are stored, how long they are retained, and whether sensitive apps or sites can be excluded.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (5)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: This skill is explicitly designed to inspect active screen captures and may proactively message the user, but the description and instructions do not clearly warn the user about this monitoring behavior. In a screen-observation skill, lack of explicit notice undermines informed consent and increases the chance of collecting or acting on sensitive visual data without the user's clear awareness.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The silent mode says to 'record the context for potential future daily summaries' without disclosing retention, logging, or storage boundaries. Because the skill processes screen context, this could result in sensitive on-screen information being stored or summarized later without explicit transparency, which creates privacy and compliance risk.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: Guardian mode describes tracking time spent on domains and applications and alerting on thresholds, but does not mention user notice, consent, or boundaries on what is monitored. Because this skill processes screen context proactively, such tracking can reveal behavioral patterns, habits, and potentially sensitive application usage, making undisclosed monitoring privacy-impacting.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: Silent mode explicitly describes background recording of screen-context observations and later summarization, but provides no indication of clear notice, consent, retention limits, or user controls. In a skill triggered by screen context webhooks, this creates a meaningful privacy and surveillance risk because sensitive on-screen data may be continuously observed and retained without the user's informed awareness.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 85% confidence
Finding: Focus mode states that the agent monitors the user's activities against a session goal and detects distractions, but does not warn that this requires behavioral surveillance of screen activity. Even if intended as a productivity aid, monitoring and classification of user behavior without clear disclosure can expose sensitive interests or work patterns and erode user trust.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.