betterlife-image-generation
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external media assets from third-party storage, which introduces a potential surface for instructions embedded within images or their metadata.
- Ingestion points: Reference images retrieved from a Supabase storage bucket (
dbbppsbtpsahdkmevxgm.supabase.co) and Google Drive. - Boundary markers: The instructions do not define specific delimiters or validation checks for the content of the retrieved images.
- Capability inventory: The skill performs network POST requests to
api.kie.aiand writes generated files to~/workspace/tool-image-generation/and/tmp/. - Sanitization: There is no mention of image sanitization, metadata stripping, or content validation before processing.
- [EXTERNAL_DOWNLOADS]: Fetches reference image assets from a Supabase storage bucket during the execution pipeline.
- [DATA_EXFILTRATION]: Transmits prompt strings and reference image URLs to the kie.ai API (
api.kie.ai) to perform image generation tasks.
Audit Metadata