The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires and installs an external binary from a third-party Homebrew tap (steipete/tap/summarize). This repository and its contents are from a source outside of the verified or trusted vendor lists.
[COMMAND_EXECUTION]: The skill uses the summarize command-line utility to process URLs and local files. This involves executing an external binary with user-provided arguments.
[PROMPT_INJECTION]: The skill processes data from untrusted external environments such as web pages and YouTube transcripts, which can contain malicious instructions intended to manipulate the AI agent.
Ingestion points: External URLs and YouTube links passed to the summarize tool as seen in SKILL.md.
Boundary markers: The instructions lack delimiters or explicit warnings to ignore instructions embedded within the processed content.
Capability inventory: The skill has the ability to execute the summarize binary via the shell.
Sanitization: No sanitization or content validation steps are identified in the skill's instructions.

summarize