The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs users to install external CLI tools and models from third-party repositories.
Evidence: Mentions npx skills add belt-sh/cli and points to https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md for installation instructions.
Impact: Relies on external code execution from sources outside the immediate skill package.
[PROMPT_INJECTION]: The skill exhibits vulnerability to indirect prompt injection where untrusted data is processed by agent capabilities.
Ingestion points: User-provided text strings are interpolated into shell commands via the prompt and text fields in SKILL.md examples.
Boundary markers: No delimiters or safety instructions are used to separate user input from system instructions.
Capability inventory: The skill utilizes the belt CLI tool for voice synthesis and media manipulation, restricted by the allowed-tools configuration.
Sanitization: The instructions do not specify any validation or sanitization steps for user-supplied prompts before they are passed to the underlying voice models.

ai-voice-cloning