herdr
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to use the
herdrcommand-line tool to manage terminal panes and execute arbitrary shell commands (e.g.,herdr pane run).- [INDIRECT_PROMPT_INJECTION]: The skill reads and interprets output from terminal panes using commands likeherdr pane readandherdr agent read. This creates a surface for indirect prompt injection where instructions embedded in terminal output could influence the agent's behavior. - Ingestion points: Terminal output retrieved via
herdr pane readandherdr agent readas described inSKILL.md. - Boundary markers: None identified; the instructions do not include specific delimiters or warnings to ignore instructions within the terminal output.
- Capability inventory: The agent can execute shell commands (
herdr pane run), start and prompt other agents (herdr agent start,herdr agent prompt), and manipulate the terminal layout. - Sanitization: The skill does not specify any sanitization or validation logic for the terminal data being read.
Audit Metadata