The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the defuddle package globally from the NPM registry (npm install -g defuddle).\n- [COMMAND_EXECUTION]: The skill operates by executing shell commands via the defuddle CLI to parse URLs or local files and integrates with the obsidian CLI for note management.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection attacks.\n
Ingestion points: Fetches arbitrary, untrusted content from the web via defuddle parse <url> (documented in SKILL.md).\n
Boundary markers: No delimiters or instructions are provided to help the agent distinguish between the skill's instructions and the content retrieved from the web.\n
Capability inventory: The skill includes the ability to execute CLI commands and write to the local file system (via the -o flag in defuddle).\n
Sanitization: There are no instructions to sanitize, escape, or validate the content retrieved from external URLs before it is processed by the agent or saved to the disk.

use-defuddle