Security audit

Jsrt Claw

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed Windows automation guide, but it gives broad local system and network execution patterns without enough user control or safety boundaries.

Install only if you intentionally want an agent to generate and run Windows JScript automation. Review every generated script before execution, avoid running it elevated, do not allow unverified remote polyfills, and require explicit approval for file changes, shell commands, WMI/environment reads, Office or Outlook access, and outbound HTTP requests.

A.I.G

Vulnerability Patterns

Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally

Findings (2)

T03 · Remote Payload Retrieval and Execution

Error

Location: SKILL.md:223
Finding: Unverified Remote JavaScript Retrieval and Execution
Content: View full analysis
Remediation: View remediation

T05 · Unauthorized Access and Privilege Escalation

Warning

Location: SKILL.md:24
Finding: Unconstrained Windows Automation Exceeds Least-Privilege Requirements
Content: View full analysis
Remediation: View remediation

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 (3)

Missing User Warnings

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill combines shell execution, WMI/system interrogation, environment-variable access, and outbound HTTP capabilities, which together enable command execution, host reconnaissance, and potential data exfiltration. Because the document frames these as available capabilities without privacy, consent, or destination restrictions, the skill context makes this substantially more dangerous than a narrowly scoped automation guide.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill explicitly instructs creation and execution of a Windows JScript file via cscript, enabling arbitrary code execution on the host. In an agent-skill context, presenting direct execution steps without safety gates, consent requirements, or clear warnings materially increases the chance of unsafe system modification or abuse.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill advertises file write, delete, and directory manipulation capabilities through COM objects without guardrails or warnings about data loss. In practice, an agent using this skill could overwrite or remove files on the local system, causing destructive changes even if the original intent is automation.
Content: No source excerpt is available for this finding.