The Agent Skills Directory

[Indirect Prompt Injection] (SAFE): The skill defines functions like imagen3Generate that process user-provided text prompts. This represents an ingestion point for untrusted data. However, since the skill consists only of documentation and lacks executable scripts or high-privilege capabilities (like file system or network access beyond the API), the risk is negligible.
[Malicious Patterns] (SAFE): No evidence of prompt injection, obfuscation, hardcoded credentials, or persistence mechanisms was found in the skill metadata or function descriptions.
[Unverifiable Dependencies] (SAFE): No external packages or remote scripts are referenced or executed.

Imagen 3