The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the infsh CLI tool to interact with the inference.sh API. This is the primary function and is correctly scoped in the skill's allowed tools metadata.\n- [EXTERNAL_DOWNLOADS]: The skill documentation includes instructions for adding external skills from the inference-sh repository via the npx skills add command. These are standard dependencies for the provided functionality.\n- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by design, as it takes user text to generate videos.\n
Ingestion points: User prompt strings are ingested into the --input field of the infsh command as shown in SKILL.md examples.\n
Boundary markers: There are no explicit markers used to separate user-provided content from the command-line arguments.\n
Capability inventory: The skill is granted permission to execute infsh commands within a Bash environment.\n
Sanitization: The skill does not perform any validation or sanitization of the user input before it is passed to the video generation tool.

p-video