The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill utilizes npx to download and execute the minion-fetch package from the NPM registry at runtime.
[COMMAND_EXECUTION]: The skill uses shell commands to invoke the fetching tool with various arguments such as headers, methods, and processing flags.
[PROMPT_INJECTION]: The skill processes content from external URLs, creating a surface for indirect prompt injection where malicious instructions embedded in a web page or API response could attempt to influence the agent's behavior.
Ingestion points: External content retrieved from URLs via the minion-fetch command.
Boundary markers: None specified; fetched content is returned to the agent without explicit delimiters.
Capability inventory: Network access (fetching), JSON transformation via jq, and HTML-to-Markdown conversion.
Sanitization: No explicit sanitization or filtering of the remote content is described in the skill's instructions.

minion-fetch