Adobe Firefly API Batch Image Generator
Pass
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data access were detected.
- [PROMPT_INJECTION]: The skill ingests data from CSV manifests, which creates a surface for indirect prompt injection. Ingestion points: CSV files (prompts, style references, aspect ratios). Boundary markers: Absent. Capability inventory: Adobe Firefly API (network) and local asset storage (file-write). Sanitization: The skill validates image dimensions and file sizes but does not specify sanitization for natural language prompts. This surface is considered a low-risk inherent feature of the skill's purpose.
- [COMMAND_EXECUTION]: Installation instructions reference npx and clawhub for deployment from the vendor's repository, which are standard and safe installation methods for this skill.
Audit Metadata