The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @runcomfy/cli package from the NPM registry using npm i -g @runcomfy/cli or npx. This is the primary tool for interacting with the service.\n- [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute runcomfy commands for authentication and image processing as defined in the allowed-tools metadata.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the ingestion of untrusted external content.\n
Ingestion points: The image and image_urls parameters within the JSON input for the runcomfy run command in SKILL.md.\n
Boundary markers: Absent. There are no explicit delimiters or instructions to ignore embedded content within the processed image URLs or prompts.\n
Capability inventory: The skill has the capability to execute shell commands via Bash(runcomfy *) across its operational flow.\n
Sanitization: Absent. The skill relies on the CLI tool's handling of input and does not implement independent sanitization or validation of the external assets or prompt strings.

relight