Security audit
Security checks for vulnerabilities and agentic risk
This skill is a straightforward Seedance/Ark video-generation helper that openly sends prompts and image URLs to Volcengine and shows no hidden persistence or local data access.
Install this only if you intend to use ByteDance/Volcengine Ark for video generation. Prompts, image URLs, request metadata, and the resulting task data are sent to that external service, so avoid confidential, personal, internal-only, or non-public image inputs unless you have approval to share them. Keep ARK_API_KEY in an environment variable and do not paste it into prompts or shared files.
This markdown file presents all contributor instructions in Chinese and does not offer an English alternative, language selection, or any opt-in mechanism. Under the policy rule for natural-language violations, forcing a specific language without user choice can be a locale-policy issue unless the restriction is clearly documented and justified.
The trigger conditions are broad enough to activate this skill for generic video-generation requests, which can cause the agent to route users into an external third-party workflow unexpectedly. That increases the chance of sending prompts or image URLs to Ark when the user did not specifically intend to use this provider or consent to external transmission.
The skill instructs users to send prompts and image URLs to a third-party API but does not warn that user content will leave the local environment and be processed by ByteDance/Volcengine. In a skill that handles creative prompts and potentially user-supplied images, omission of a privacy notice can lead to accidental disclosure of sensitive data.
This example performs an authenticated POST to an external service and transmits user-provided prompt text and an image URL to a third-party API. In the context of an agent skill, external transmission is expected for the feature, but it is still security-relevant because it can expose user content and metadata if the user is not clearly informed or if routing occurs too broadly.
# 1. 创建图生视频任务
resp=$(curl -s -X POST 'https://ark.cn-beijing.volces.com/api/v3/contents/generations/tasks' \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $ARK_API_KEY" \
-d '{
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
echo "Task ID: $task_id"
# 2. 轮询任务状态
curl -s "https://ark.cn-beijing.volces.com/api/v3/contents/generations/tasks/$task_id" \
-H "Authorization: Bearer $ARK_API_KEY"
# 3. 当 status 为 succeeded 时，从响应的 content 中取 video_url
This is another authenticated external POST example that sends prompts and image URLs to Ark, carrying the same privacy and data-sharing risk as the earlier task-creation example. Because this is sample code users may copy directly, it can normalize external transmission without adequate warning about third-party processing.
curl -X POST https://ark.cn-beijing.volces.com/api/v3/contents/generations/tasks \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $ARK_API_KEY" \
-d '{
The operational instructions are presented entirely in Chinese, while the manifest description is partly English, and there is no indication that the user can choose their preferred language. This can violate language/locale policy where skills should not impose a specific language without opt-in or documented justification.
No suspicious patterns detected.