ClawHub
Back to skill

Security audit

p-video

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Pruna video-generation skill; it uses external uploads and API keys as expected for making videos, with no evidence of hidden or destructive behavior.

Install only if you are comfortable sending selected prompts, images, video frames, and audio to Pruna or related providers. Use it with files you intentionally provide, avoid uploading sensitive media or secrets, and keep PRUNA_API_KEY or REPLICATE_API_TOKEN in environment variables rather than hardcoding or sharing them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Low
Confidence
86% confidence
Finding
The description is broad enough to trigger on many general creative or media-generation requests, which can cause the agent to invoke this skill in situations where a more specific tool or safer workflow would be more appropriate. While this is not directly exploitable as code execution, overly broad activation boundaries increase the attack surface for prompt-routing mistakes, unintended tool use, and user confusion.

External Transmission

Medium
Category
Data Exfiltration
Content
## File uploads

1. `POST /v1/files` with `-F "content=@/path/to/file.jpg"` and `apikey` header.
2. Use `urls.get` from the response (or construct `https://api.pruna.ai/v1/files/{id}`) as the **`image`**, **`last_frame_image`**, **`images[]`**, **`person_image`**, **`garment_images[]`**, **`audio`**, etc. value in `input`.

Uploaded files expire (see upload response `expires_at`).
Confidence
76% confidence
Finding
https://api.pruna.ai/

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.