The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill retrieves a task catalog from the author's official domain (signals.forwardfuture.com) to provide users with pre-defined automation templates. This uses the vendor's own infrastructure for intended functionality.
[PROMPT_INJECTION]: The skill processes untrusted input from code repositories and conversation histories. It includes robust defensive instructions to ensure the agent treats this external content strictly as data and ignores any embedded instructions, effectively mitigating indirect prompt injection risks.
[COMMAND_EXECUTION]: The workflow involves executing bounded tasks within user-authorized environments. It incorporates strict safety checks, requiring explicit human-in-the-loop approval for destructive, financial, or privacy-sensitive operations and preventing autonomous schedule or production changes.

loop-library