Security audit
Security checks for vulnerabilities and agentic risk
This skill is a straightforward SiliconFlow image-generation helper, with expected external API use, but users should avoid putting sensitive text in prompts and should choose an explicit output path.
Install only if you are comfortable sending image prompts to SiliconFlow under your API key. Do not include secrets, proprietary text, or personal data in prompts; specify your own output file instead of relying on the default /tmp path; and avoid running the script with elevated privileges.
scripts/generate.sh:7Predictable Temporary Output Allows Symlink-Based File Overwrite
scripts/generate.sh:22Unescaped User-Controlled Values Are Interpolated into a JSON Request
Without declared permissions the skill's intent is opaque and cannot be validated.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
curl -X POST "https://api.siliconflow.cn/v1/images/generations" \
-H "Authorization: Bearer $SILICONFLOW_API_KEY" \
-H "Content-Type: application/json" \
-d '{
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
curl -X POST "https://api.siliconflow.cn/v1/images/generations" \
-H "Authorization: Bearer $SILICONFLOW_API_KEY" \
-H "Content-Type: application/json" \
-d '{
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
curl -X POST "https://api.siliconflow.cn/v1/images/generations" \
-H "Authorization: Bearer $SILICONFLOW_API_KEY" \
-H "Content-Type: application/json" \
-d '{
This code sends user-controlled content and an authorization-bearing request to an external API endpoint, creating a clear data egress path. In the context of an agent skill, this is security-relevant because users may assume local processing, while prompts and related metadata are actually disclosed to a remote service.
echo "Generating image with $MODEL..."
echo "Prompt: $PROMPT"
RESPONSE=$(curl -s -X POST "https://api.siliconflow.cn/v1/images/generations" \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d "{
This code sends user-controlled content and an authorization-bearing request to an external API endpoint, creating a clear data egress path. In the context of an agent skill, this is security-relevant because users may assume local processing, while prompts and related metadata are actually disclosed to a remote service.
echo "Generating image with $MODEL..."
echo "Prompt: $PROMPT"
RESPONSE=$(curl -s -X POST "https://api.siliconflow.cn/v1/images/generations" \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d "{
The script transmits the full user-provided prompt to a third-party image-generation service without any explicit consent, warning, or data-minimization controls. If users include sensitive, proprietary, or personal information in prompts, that data is exposed to the external provider and may be logged, retained, or processed outside the local environment.
No suspicious patterns detected.