The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill documentation provides instructions for installing the freeze utility from its official GitHub repository and via Homebrew. These are well-known sources for developer tools. The instructions include a regional Go proxy mirror and a flag to disable checksum verification (GOSUMDB=off), which is documented as a workaround for specific network environments during manual installation by the user.
[COMMAND_EXECUTION]: The render_ansi.sh script executes local binaries (freeze or Google Chrome) to perform image rendering. The script safely quotes variables derived from command-line arguments to prevent command injection vulnerabilities.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted terminal output.
Ingestion points: Processes .ansi files generated from various CLI tools as described in SKILL.md.
Capability inventory: Executes rendering commands in render_ansi.sh and file operations in ansi2html.py.
Sanitization: The ansi2html.py script correctly utilizes html.escape() to sanitize terminal output before wrapping it in HTML for rendering, mitigating the risk of injection through the browser fallback path.

terminal-screenshot