The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the herdr CLI to execute arbitrary commands within managed terminal panes via the herdr pane run and herdr agent prompt commands.
[INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface for indirect prompt injection by reading and processing output from external terminal sessions and subagents.
Ingestion points: Data is ingested through herdr pane read, herdr agent read, and herdr pane wait-output as described in SKILL.md.
Boundary markers: The instructions do not specify any delimiters or warnings to the agent to ignore potentially malicious instructions embedded in the terminal output.
Capability inventory: The skill has the ability to execute shell commands (herdr pane run), start and configure new subagents (herdr agent start), and transmit prompts to other agents (herdr agent prompt).
Sanitization: There is no mention of sanitization, validation, or escaping of the content read from panes before it is interpreted by the agent.

herdr