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.ai and 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
Risk Level
SAFE
Analyzed
Sep 2, 2026, 09:39 PM
Security Audit — agent-trust-hub — betterlife-image-generation