task-handoff

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill generates and describes the use of ai-handoff and ai-coord command-line tools. These are described as local tools for managing project metadata and task transitions within a development environment. The skill specifically warns the agent not to execute the generated launch commands itself, but rather to present them to the user or the receiving session.
  • [REMOTE_CODE_EXECUTION]: While the skill mentions an 'authenticated Codex CLI' for generated commands, it does not perform remote code execution itself. It acts as a generator for structured documentation and local commands.
  • [DATA_EXPOSURE]: The skill requires access to repository metadata and working-tree state to summarize the current task status. This is a standard requirement for the skill's purpose (task handoffs) and does not involve unauthorized access or exfiltration to external domains.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 09:30 AM