The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes the himalaya command-line utility and Python scripts to list, read, and send emails.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external IMAP servers, which could contain malicious instructions for the agent.
Ingestion points: Data is fetched from external mailboxes via himalaya envelope list and himalaya message read as described in SKILL.md.
Boundary markers: The instructions lack specific delimiters or boundary markers to distinguish email content from system instructions.
Capability inventory: The skill includes the ability to execute shell commands, run Python scripts, and perform network operations to interact with mail servers.
Sanitization: The skill does not implement or describe any sanitization, filtering, or validation of the fetched email content before it is presented to the agent.

himalaya