handover
Pass
Audited by Gen Agent Trust Hub on Jun 30, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [SAFE]: No security issues or malicious patterns were identified in the skill instructions. The skill describes a legitimate administrative workflow for task delegation.
- [NO_CODE]: The skill consists entirely of markdown documentation. It does not include any scripts, binary files, or external package dependencies.
- [PROMPT_INJECTION]: The skill manages a task delegation process that involves ingesting untrusted user input. 1. Ingestion points: User tasks via /handover and subagent results from handoff docs. 2. Boundary markers: Absent; tasks are passed verbatim. 3. Capability inventory: Spawning subagents via Task or Agent tools. 4. Sanitization: Absent; the skill relies on platform-level guardrails for safety.
Audit Metadata