Security audit
Security checks for vulnerabilities and agentic risk
ClawScan marks this skill benign because its reported external service use fits its stated generation purpose, though the scanners also flag an unpinned install example and missing privacy disclosures.
Before installing, consider whether you are comfortable sending selected reference images and prompts to Varg and any downstream model providers. Avoid private or sensitive material unless you understand and accept that processing, and note that the install example does not pin a version. The scan was partial because two local references could not be resolved, so the evidence is incomplete.
The example runs an unpinned npm package through npx, potentially executing a newly published or compromised version with the user's privileges. This is a dependency supply-chain risk, although the finding incorrectly describes the command as an MCP server reference.
The examples invite use of local stills and a character photograph without explaining that their contents must be processed by external generation services. Naming the cloud services provides context, but does not establish informed authorization to disclose potentially private images.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
Kling 4 knows what a tail whip, a head spin or a freeze looks like and can string several of them into one 30-second take with its own cuts, camera moves and sound. What it needs from you is the look and the key poses, as stills. The prompt can be one line. This is how the breakdance, scooter and BMX sequences in fal's Kling 4 Halloween film were made ([YouTube, 2026-10-30](https://www.youtube.com/watch?v=WzXKggH-0Io%29%29%3A "really high level prompt, but extremely guided visually".
Generation runs on varg: REST `https://api.varg.ai/v2` (the `varg-ai` skill) or the MCP server `https://mcp.varg.ai/mcp`.
## 1. Ask, then go
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
curl -s -X POST https://api.varg.ai/v2/tools/video/call -H "Authorization: Bearer $VARG_API_KEY" \
-H "Content-Type: application/json" -d '{
"model": "fal:fal-ai/kling-video/v4/reference-to-video",
"prompt": "<the one-line prompt>",
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
curl -s -X POST https://api.varg.ai/v2/tools/video/call -H "Authorization: Bearer $VARG_API_KEY" \
-H "Content-Type: application/json" -d '{
"model": "fal:fal-ai/kling-video/v4/reference-to-video",
"prompt": "<the one-line prompt>",
The workflow submits prompts and reference-image URLs to an external generation endpoint without a privacy or sensitive-input checkpoint. Although external processing is central to the advertised functionality, private images, confidential prompts, or access-bearing image URLs could be disclosed without an adequately informed user decision.