herdr

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill enables the agent to execute shell commands in separate terminal panes through the herdr pane run utility. While this is the core function of the skill, it allows for arbitrary command execution within the Herdr environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to read and interpret data from terminal buffers, creating a surface for indirect prompt injection if the terminal output contains malicious instructions.
  • Ingestion points: Content is ingested from files, terminal viewports, and process snapshots using herdr agent read, herdr pane read, and herdr pane wait-output.
  • Boundary markers: The skill lacks explicit instructions for using delimiters or boundary markers to isolate potentially adversarial terminal content from the agent's instructions.
  • Capability inventory: The agent possesses the capability to run system commands (herdr pane run), start and control secondary agents (herdr agent start, herdr agent prompt), and manipulate the terminal layout.
  • Sanitization: There are no specified procedures for sanitizing or validating terminal output before it is processed as context by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 10:05 AM