Security audit

真人 cosplay 套图（ComfyUI 本地出图）

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because its instructions recommend bypassing PowerShell safeguards without a warning; the review found no confirmed malicious behavior, but coverage is partial.

Before installing, review the PowerShell troubleshooting advice and avoid running blocked scripts through a bypass or `Invoke-Expression` unless you have inspected the exact script and trust its source. The scan is partial: five local path-like references could not be matched to bundled files, so the evidence does not cover everything those references may point to.

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
Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

PowerShell execution-policy bypass is recommended without a user-facing warning.

Medium

Category: Output Handling
Confidence: 94% confidence
Finding: The troubleshooting guidance explicitly recommends evaluating script contents with Invoke-Expression or using ExecutionPolicy Bypass when PowerShell blocks execution, without requiring script inspection or explaining the risk. Although execution policy is not a security boundary, this advice encourages an agent to circumvent an execution safeguard; if the referenced script is untrusted or modified, it could execute arbitrary commands with the agent's permissions. The local image-generation context suggests a convenience workaround rather than malicious intent.
Content: No source excerpt is available for this finding.

Ae4

Medium

Category: analysis-evasion
Confidence: 80% confidence
Finding: Suspicious Unicode normalization or mixed-script content
Content: No source excerpt is available for this finding.