kepu-quickcut

• Outcome: Pass
• Latest audit: Nov 8, 2026 · 3:49 AM UTC
• Version: 1.1.0

Overview

ClawScan marks this skill benign with medium confidence: the scanners found no reported security issues, while noting some non-security concerns and incomplete inspection of several files.

The benign verdict is not a guarantee of safety, and confidence is medium. Consider that four of fourteen components were only partially inspected; review those components or seek a more complete scan if that uncertainty matters to you. The reported animation-label behavior may also affect consistency.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Incomplete referenced artifact analysis

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 25)May include surrounding context.

md

| 机制机器 | `templates/machine.html` | 开场先亮骨架 → 零件逐个点亮、小球沿管道流动 → 反馈回路（可选）→ 尾屏点破 | 系统/机制/流程：Agent 工作流、RAG、数据流水线 |

Incomplete referenced artifact analysis

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 40)May include surrounding context.

md

NODE_PATH=<playwright-core 所在的 node_modules> node scripts/capture.js preview 抽帧

Incomplete referenced artifact analysis

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 53)May include surrounding context.

md

node scripts/capture.js <anim.html> <frames_dir> # 300 帧，约 43 秒

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_read.

Medium

• Category: MCP Least Privilege
• Confidence: 70% confidence

Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Moon-phase labels depend on previous seek calls, contradicting the manifest's deterministic frame-reproduction guarantee.

Low

• Category: Excessive Agency
• Confidence: 99% confidence

Finding

The manifest promises that each frame is determined solely by seek(t), but phase labels are only conditionally updated or hidden. Calling seek(2.5) followed by seek(3.3) leaves the previous moon-phase label visible, whereas calling seek(3.3) immediately after initialization leaves it hidden; the same timestamp therefore produces different frames.

Content

No source excerpt is available for this finding.