fal-vision
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill documentation references an external repository at
github.com/fal-ai-community/skillsfor its implementation and assets. This reference targets a well-known service and organization. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted visual data, creating a potential surface for instructions embedded in images or OCR text.
- Ingestion points: The skill processes images for analysis and description as described in
SKILL.md. - Boundary markers: No specific delimiters or instructions to ignore embedded text in images are present in the skill metadata.
- Capability inventory: The skill performs object detection, OCR, and visual question answering.
- Sanitization: No evidence of visual content filtering or instruction sanitization is provided in the documentation.
Audit Metadata