The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill's primary functionality is to download files and fetch remote data from URLs provided by the user using the wget utility.
[COMMAND_EXECUTION]: The skill executes shell commands using wget. It includes instructions to quote URLs and validate formats to prevent potential command injection vulnerabilities.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external URLs, which creates a surface for indirect prompt injection where instructions embedded in the downloaded content could influence the agent.
Ingestion points: Data fetched from URLs provided at runtime (SKILL.md).
Boundary markers: None provided for the content returned by wget to stdout.
Capability inventory: Shell command execution via wget and file system writes via the -O flag.
Sanitization: The skill recommends URL format validation and quoting of variables, though it does not specify content sanitization for the downloaded data.

wget-reader