Security audit

Malware Analyst

Security checks for vulnerabilities and agentic risk

Overview

This skill is defensive in purpose but needs Review because it tells agents to execute malware samples without strong containment and authorization requirements at the action point.

Install only if you will use it for authorized defensive malware analysis in an isolated, disposable lab. Before running any sample, require explicit authorization, snapshots or rollback, no production access, and controlled or simulated networking. Treat the file-identification trigger text as incomplete because the skill actually covers broader malware-analysis workflows.

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

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Missing User Warnings

High

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill gives step-by-step instructions to execute a malware sample and trigger functionality, but the execution flow lacks prominent, explicit safety gates at the point of action. Even in a defensive skill, telling users to run malware without hard requirements for isolation, containment, non-production systems, and legal authorization materially increases the risk of accidental infection, lateral movement, or unintended outbound communication.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The manifest description at L004 presents a full malware-analysis skill, and the body indeed contains extensive malware-analysis procedures. However, the 'Use this skill when' and 'Do not use this skill when' sections narrow the scope to file identification, which contradicts the much broader behavior and instructions elsewhere in the file such as dynamic analysis, persistence/evasion analysis, IOC extraction, and full reporting.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: This is not just incomplete documentation; it actively contradicts the rest of the file. The sections on static analysis, dynamic analysis, malware techniques, IOC extraction, and reporting show a much broader intent than the 'file identification' limitation stated in the usage guidance.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The trigger conditions are overly broad and could cause the skill to be invoked for generic 'analysis/help' requests where malware-analysis procedures are unnecessary or inappropriate. In a sensitive domain, loose activation criteria increase the chance of exposing users to high-risk instructions, including dynamic execution guidance, outside a properly controlled defensive context.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.