Security audit
Security checks for vulnerabilities and agentic risk
ClawScan rates this skill benign with medium confidence: the findings are consistent with its video-generation purpose, while its install reference and handling of external media merit attention.
The verdict is benign, not risk-free. Before installing, consider that the install command is unpinned and the workflow sends prompts and reference media to external services. Avoid submitting private or sensitive media unless you are comfortable sharing it. The scan was partial because three local path-like references could not be resolved, so the evidence is incomplete.
The installation command executes an unversioned npm CLI and installs skill content from an unpinned repository reference. Although this is not an MCP server declaration as the finding suggests, mutable dependencies create a supply-chain risk: a compromised release or repository update could introduce code or agent instructions running with the user's privileges.
The example instructs the agent to create a Kling 4 element from two local character images, rather than merely listing an available tool. This requires submitting those images to the external generation service, but the README does not disclose that transfer or warn about using private or sensitive photos; listing the varg API and account requirement does not explain this privacy impact.
The skill instructs the agent to submit frame URLs and prompts to Varg using a fal-backed generation route, and supports references containing people's photos and voices. Although the services are named, the skill never warns that these inputs are shared externally or advises against submitting sensitive media without authorization.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
kling_v4 routes by input: text only → text-to-video; one or two images → image-to-video, where image 1 is the start frame and image 2 the end frame. (Before api#239 reached production, a third image was silently dropped there too; now three or more go to reference-to-video.) For key frames as references, always pin the reference route by its key:
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",
"files": [{"url": "FRAME_1"}, {"url": "FRAME_2"}, {"url": "FRAME_3"}],
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
kling_v4 routes by input: text only → text-to-video; one or two images → image-to-video, where image 1 is the start frame and image 2 the end frame. (Before api#239 reached production, a third image was silently dropped there too; now three or more go to reference-to-video.) For key frames as references, always pin the reference route by its key:
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",
"files": [{"url": "FRAME_1"}, {"url": "FRAME_2"}, {"url": "FRAME_3"}],