ClawHub
Back to skill

Security audit

Veo 3.1

Security checks across malware telemetry and agentic risk

Overview

This is a coherent NanoPhoto.AI video-generation skill that sends user-provided prompts, image URLs, task IDs, and an API key to the advertised service.

Install this only if you intend to use NanoPhoto.AI and are comfortable sending that service your prompts, referenced public image URLs, task IDs, and API key for processing. Do not submit confidential, regulated, private, or unauthorized media unless your organization approves that third-party data sharing, and store the API key in the skill env setting rather than in chat.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill documentation indicates capabilities to read environment variables, read local config files, and make network requests, but it does not explicitly declare permissions for those behaviors. This reduces transparency and informed consent, especially because the bundled script can read credentials from both the environment and ~/.openclaw/openclaw.json before transmitting data to a third-party API.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill sends prompts, image URLs, task IDs, and an API bearer token to NanoPhoto.AI, but the introductory sections do not give a clear privacy/security warning that user content leaves the local environment and is processed by an external service. Users may unknowingly submit sensitive prompts or URLs, creating confidentiality and privacy risk.

External Transmission

Medium
Category
Data Exfiltration
Content
### Submit generation

```bash
curl -X POST "https://nanophoto.ai/api/veo-3/generate" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $NANOPHOTO_API_KEY" \
  --data-raw '{
Confidence
92% confidence
Finding
curl -X POST "https://nanophoto.ai/api/veo-3/generate" \ -H "Content-Type: application/json" \ -H "Authorization: Bearer $NANOPHOTO_API_KEY" \ --data-raw '{ "shots": [ { "id":

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.