The Agent Skills Directory

[SAFE]: The skill follows security best practices by advising the agent not to run external installers and to avoid reading authentication tokens from the environment.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-provided text for audio synthesis, representing an indirect prompt injection surface.
Ingestion points: The <text> parameter used in the edgespeak-cli speech command described in SKILL.md.
Boundary markers: Instruction templates use double quotes to encapsulate input text.
Capability inventory: The skill executes shell commands (edgespeak-cli) and writes audio files to the local filesystem.
Sanitization: No explicit sanitization or filtering of input text is defined in the instructions.
[EXTERNAL_DOWNLOADS]: The skill references an external installation URL and a CLI update mechanism.
URL: https://edgespeak.com/docs/cli#install (referenced for user-driven installation).
Logic: The skill explicitly commands the agent to point the user to the installation steps rather than executing the installer itself, which is a safe practice.

edgespeak-broadcast