ClawHub
Back to skill

Security audit

generate-poster

Security checks across malware telemetry and agentic risk

Overview

The skill mostly does what it claims, but its examples handle a live Flyelep API key in local temp files and inline shell commands in a way users should review first.

Install only if you are comfortable sending product descriptions, reference image URLs, and your Flyelep API key to Flyelep. Prefer a safer HTTP client or secret-handling method that avoids writing the key to payload_temp.json or embedding it in shell commands, and rotate the key if it may have been exposed in local files, logs, or command history.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Context-Inappropriate Capability

Medium
Confidence
92% confidence
Finding
The skill’s stated purpose is to call an HTTP API, but it instructs the agent to invoke a shell and create local temporary files containing request payloads. That unnecessarily expands the capability surface from a simple network call to local command execution and file writes, increasing risk of credential exposure, unsafe command construction, and residual sensitive artifacts on disk.

Intent-Code Divergence

Medium
Confidence
95% confidence
Finding
The documentation claims the API key is only transmitted at request time and not stored, but later examples explicitly write the secretKey into payload_temp.json and sometimes place it inline in shell commands. This creates a mismatch that can mislead users into exposing credentials in local files, shell history, logs, backups, or crash artifacts.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill instructs users to place the API secret in temporary files and inline curl commands without adequately warning that secrets may persist in shell history, process listings, terminal logs, or on-disk artifacts. Because the skill handles a live credential, these examples normalize insecure secret-handling practices and can lead to credential compromise outside the API itself.

External Transmission

Medium
Category
Data Exfiltration
Content
- **方式 B（无 Write 工具）**：使用 Shell 的 .NET API 创建文件（`Set-Content -Encoding UTF8` 会带 BOM，不可用）
- **macOS/Linux 环境**：
  - bash/zsh 默认使用 UTF-8 编码，可直接内联中文 JSON，无需临时文件。命令中使用 `curl`（无需 `.exe`，无需 `--%`）。
  - 推荐内联写法：`curl -X POST URL -H "..." -H "..." --data-binary 'JSON单行内容'`，一步完成。
  - 也可使用临时文件方式：`curl --data-binary @payload_temp.json`。
- **清理**：API 返回结果后，务必删除 `payload_temp.json` 临时文件（如使用了临时文件）。
Confidence
84% confidence
Finding
curl -X POST URL -H "..." -H "..." --data-binary 'JSON单行内容'`，一步完成。 - 也可使用临时文件方式：`curl --data-binary @payload_temp.json`。 - **清理**：API 返回结果后，务必删除 `payload_temp.json` 临时文件（如使用了临时文件）。 ### 示例 1：生成产品主图（

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.