ClawHub
Back to skill

Security audit

varg-product-hook

Security checks for vulnerabilities and agentic risk

Overview

This skill creates product videos through a disclosed external service, with no evidence of hidden access or harmful actions.

Use photos you are comfortable sharing with varg and check estimated generation costs before rendering. Review synthetic product claims and required AI labels before publishing. Companion skills require separate review.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 33)May include surrounding context.

md
The hook is the first 5-15 seconds of a product reel: real-looking footage of the product doing the one thing that makes people stop. In the dropshipping reels this skill was built from (@tradelle, Sept-Oct 2026), the hook carried the video: a snake biting a leg gaiter, a worker getting sand and grinder sparks thrown at his face mask, a cat's claw lit up by an LED clipper. The voiceover over the hook is a plain product line ("These are the leg guards I wear when I'm outdoors"). Two more reels (a cat runner, drink-test nail stickers) show the other use: the hook stretched into the whole 15-22 s ad, "The problem → Vs → The solution", set to music with no voice (section 3).

Generation runs on varg: the `varg-ai` skill (REST at `https://api.varg.ai/v2`) or the varg MCP server (`https://mcp.varg.ai/mcp`, tools `call_tool` + `get_job`). Every call returns a job; poll `GET /v2/jobs/{id}` until `completed`, the file is at `output.outputs[0].url`.

## 1. Ask two things first

Context Window Stuffing

Medium
Category
Memory Poisoning
Confidence
85% confidence
Finding

Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.

Content

Scanner excerpt · SKILL.md (reported line 56)May include surrounding context.

md
Save the 2-3 best references with the `media-download` skill (`vdl <url>`) to study the shots. Write down the idea in one line ("snake strikes the gaiter in a swamp, the gaiter holds"); you remake the idea, not the clip.

## 3. Pick the archetype and fill the prompt

Every prompt has five blocks (the order matters for Seedance 2.5):

The workflow uploads user-provided product photos to an external service without a privacy warning.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The skill instructs the agent to upload collected product photos to varg and submit them for video generation. Although the service is named, there is no user-facing warning that the photos will leave the user's environment for third-party processing, which could expose confidential product imagery or incidental personal information.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 102)May include surrounding context.

Upload the product photos (POST /v2/files, MCP create_upload → PUT to proxy_url), then:

bash
curl -s -X POST https://api.varg.ai/v2/video \
  -H "Authorization: Bearer $VARG_API_KEY" -H "Content-Type: application/json" \
  -d '{
    "model": "seedance_2_5",

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 102)May include surrounding context.

Upload the product photos (POST /v2/files, MCP create_upload → PUT to proxy_url), then:

bash
curl -s -X POST https://api.varg.ai/v2/video \
  -H "Authorization: Bearer $VARG_API_KEY" -H "Content-Type: application/json" \
  -d '{
    "model": "seedance_2_5",