tigris-image-optimization
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references and provides installation instructions for established third-party libraries including sharp, Pillow, django-imagekit, and intervention/image. These are standard tools for image processing and are appropriate for the skill's functionality.
- [INDIRECT_PROMPT_INJECTION]: The skill processes image files, which provides a surface for instructions embedded in data. 1. Ingestion points: Untrusted image data enters via request handlers in resources/django.md, resources/express.md, resources/laravel.md, resources/nextjs.md, and resources/remix.md. 2. Boundary markers: Absent; the skill provides code templates for application logic rather than agent instructions. 3. Capability inventory: Writing to Tigris storage (all resource files) and executing image processing via Sharp and Pillow. 4. Sanitization: Absent in templates; relies on the security of the underlying image libraries.
Audit Metadata