The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @runcomfy/cli package via npm. This is a verified vendor resource from RunComfy used to interact with the service API.
[PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks as it ingests untrusted media assets. Ingestion points: image_url, audio_url, reference_video_url, images, and image_urls fields in SKILL.md. Boundary markers: Present; the skill explicitly instructs the agent to only ingest URLs provided by the user and to suspect assets if output behavior diverges from expectations. Capability inventory: Subprocess calls via runcomfy run in the Bash tool. Sanitization: Absent; the skill relies on the underlying CLI and API for input validation.
[COMMAND_EXECUTION]: The skill utilizes the Bash(runcomfy *) tool. By restricting the agent to the runcomfy command prefix in the allowed-tools frontmatter, it mitigates the risk of arbitrary shell command execution.

face-swap