The Agent Skills Directory

[SAFE]: The skill is a legitimate integration for the inference.sh platform, providing users with commands to generate AI media using official tools.
[COMMAND_EXECUTION]: The skill provides examples for executing the infsh command. The execution environment is restricted to the infsh tool as defined in the allowed-tools section of the YAML frontmatter.
[EXTERNAL_DOWNLOADS]: References installation scripts and related skills located on the official GitHub repository for the vendor (inference-sh/skills). These are verified vendor resources and do not pose a third-party supply chain risk.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it processes external data from URLs (images, audio, video).
Ingestion points: image_url, audio_url, and video_url parameters in the infsh app run commands (SKILL.md).
Boundary markers: Absent; the skill relies on the underlying models and CLI for input handling.
Capability inventory: Commands are limited to the infsh CLI tool via Bash (SKILL.md).
Sanitization: No explicit sanitization or validation of external URLs is performed within the instructions.
Note: This is a low-level risk inherent to any tool that processes untrusted external media.

ai-avatar-video