The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the infsh CLI tool for all core functions, including logging in and running inference models. The allowed-tools header correctly limits the agent's scope to this specific utility using the Bash(infsh *) pattern.- [EXTERNAL_DOWNLOADS]: The skill points to external resources for installation and enhancement, specifically fetching instructions from raw.githubusercontent.com/inference-sh/skills and utilizing npx to install additional skill packages. These resources are part of the platform's official distribution channel.- [PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection, as it processes user-supplied text for the prompt argument in various image generation models without implementing explicit sanitization or boundary delimiters.
Ingestion points: The --input argument in the infsh app run commands found in SKILL.md.
Boundary markers: Absent; user inputs are directly included in the JSON payloads.
Capability inventory: The infsh tool performs network operations and likely writes resulting image data to the local file system.
Sanitization: No sanitization or escaping mechanisms are described or implemented in the provided instructions.

ai-image-generation