terminal-execution
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines standard shell patterns for capturing command output to local files (e.g., using redirection to .tmp/copilot/). No suspicious network activity, credentials, or malicious commands are present.\n- [COMMAND_EXECUTION]: The skill promotes the use of structured execution tools like the
terminal-runnerMCP server to ensure visibility of exit codes and stdout/stderr.\n- [SAFE]: Indirect Prompt Injection Surface:\n - Ingestion points: Reading command output redirected to files in
.tmp/copilot/(SKILL.md)\n - Boundary markers: Absent\n
- Capability inventory: Shell command execution via
execute_commandandrun_in_terminal(SKILL.md)\n - Sanitization: None
Audit Metadata