ClawHub
Back to skill

Security audit

Duanshipinjiexi

Security checks across malware telemetry and agentic risk

Overview

The skill largely matches its video-parsing purpose, but it should be reviewed because it can automatically send user links and identity codes to a newly discovered, unverified backend service.

Review before installing. Use it only if you are comfortable sending video links, generated identity codes, and purchase/status information to the service operator. Avoid relying on the automatic URL fallback unless the backend source is verified or manually approved, because it can redirect future parsing requests to a different service host.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Context-Inappropriate Capability

Medium
Confidence
92% confidence
Finding
The fallback logic retrieves a remote skill package and metadata, extracts a Base URL, and then trusts that value to contact a new backend. This creates an untrusted dynamic service-discovery channel outside the stated video parsing function, so a compromised registry, package, or metadata response could silently redirect users to attacker-controlled infrastructure.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The skill instructs the agent to automatically invoke external parsing and account-related actions whenever a user provides a supported link, identity code, payment status, or purchase inquiry. This broad trigger surface can cause unintended network requests, persistence of user-provided identifiers, and transactional flows without clear confirmation, increasing the risk of misuse, privacy issues, and accidental charges or state changes.

Missing User Warnings

Medium
Confidence
85% confidence
Finding
The shell snippet performs several network requests, writes downloaded content to disk, unzips files, and deletes directories without any explicit disclosure, validation, or confirmation. That increases the risk of unintended data transfer, local file side effects, and operator misuse, especially if copied into automation or executed with elevated privileges.

External Script Fetching

High
Category
Supply Chain
Content
rm -rf "$TEMP_DIR"

if [ -n "$NEW_URL" ]; then
  curl -s --max-time 30 "$NEW_URL/api/parse.php?code={CODE}&url=视频链接"
  echo "【提示】解析服务地址已更新，后续使用新地址 $NEW_URL"
else
  # 2️⃣ 兜底：从 ClawHub 查
Confidence
90% confidence
Finding
The code issues requests to a dynamically discovered external URL and passes user-supplied video-link data to that endpoint. Because the endpoint is not fixed or strongly validated, this effectively enables remote fetching from attacker-influenced infrastructure, creating risks of data exfiltration, tracking, malicious responses, or follow-on compromise through trusted operator workflows.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.