The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use the herdr CLI binary to manage terminal environments and execute shell commands within panes, such as starting development servers or running test suites.
[PROMPT_INJECTION]: The skill introduces an indirect prompt injection vulnerability by reading output from terminal panes, which could contain instructions from untrusted sources. * Ingestion points: Terminal pane content read via herdr pane read (SKILL.md). * Boundary markers: Absent; there are no instructions to use delimiters or ignore instructions found within the read data. * Capability inventory: The agent has the capability to execute arbitrary shell commands in any managed pane via herdr pane run (SKILL.md). * Sanitization: Absent; there is no evidence of filtering or escaping logic applied to data read from terminal panes before it is processed by the agent.

herdr