The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of a third-party binary via a Homebrew tap (steipete/tap/summarize) as defined in its metadata.
[COMMAND_EXECUTION]: The skill instructions direct the agent to execute the summarize command-line tool, using user-provided paths and URLs as arguments.
[PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it is designed to ingest and summarize untrusted data from arbitrary URLs, YouTube videos, and local files. 1. Ingestion points: The skill processes content from external URLs and local file paths (SKILL.md). 2. Boundary markers: No specific delimiters or instructions to ignore embedded commands are provided for handling the tool's output. 3. Capability inventory: The skill has the ability to execute shell commands and interact with model APIs. 4. Sanitization: No sanitization or validation of the ingested external content is mentioned in the skill definition.

summarize