The Agent Skills Directory

[SAFE]: Extensive review of the instructions and code examples revealed no malicious commands, obfuscated content, or unauthorized data access patterns.
[EXTERNAL_DOWNLOADS]: The skill declares dependencies on standard, well-known libraries node-fetch (NPM) and requests (pip) to facilitate API communication. It also references installation via the skills.sh CLI for the vendor's official repository.
[PROMPT_INJECTION]: The skill processes user-provided prompts and image URLs for AI generation tasks, establishing a common surface for indirect prompt injection where untrusted external data could contain embedded instructions.
Ingestion points: prompt, imageUrl, and inputImageUrls parameters defined in SKILL.md.
Boundary markers: None explicitly documented in the request construction examples.
Capability inventory: The skill is restricted to performing network POST and GET operations to the official api.letz.ai endpoint.
Sanitization: The skill does not specify input validation or sanitization logic for user-provided data before API transmission.

letzai-api