The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes code templates that use child_process.execSync to invoke FFmpeg for video conversion. This is a common practice for media processing but presents a command injection risk if the file paths or arguments are derived from untrusted user input.
[EXTERNAL_DOWNLOADS]: The documentation references downloading Chromium binaries via npx playwright install. This is the standard setup for the Playwright automation library provided by a well-known vendor.
[PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection due to its core function of navigating to and interacting with external web content.
Ingestion points: The skill visits external URLs using page.goto() (SKILL.md).
Boundary markers: Absent; the instructions do not include markers or directives for the agent to distinguish between skill instructions and commands potentially embedded in web pages.
Capability inventory: The skill has the ability to write to the local filesystem (fs.writeFile) and execute shell commands (execSync) (SKILL.md).
Sanitization: Absent; there is no mention of sanitizing or validating the content retrieved from the web before processing it.

recording