The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill references installation instructions and additional skill components from the vendor's GitHub repository (inference-sh). These external references are standard for the deployment and operation of the vendor's specialized audio tools.
[COMMAND_EXECUTION]: Employs the infsh command-line interface to interact with audio generation services. This tool execution is appropriately scoped within the skill's frontmatter configuration.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes text segments which may originate from untrusted data sources.
Ingestion points: The segments array in the JSON input for the infsh tool described in SKILL.md.
Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potential commands embedded within the text segments.
Capability inventory: The skill uses the Bash tool to run the infsh CLI across multiple examples in SKILL.md.
Sanitization: No evidence of sanitization, escaping, or validation of the input text is performed before it is passed to the generation command.

elevenlabs-dialogue