aiox-handoff
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill facilitates state persistence and context management between agents by writing YAML artifacts to a local directory (
.aiox/handoffs/). No network operations, suspicious code execution, or credential access patterns were detected.\n- [INDIRECT_PROMPT_INJECTION]: The skill functions as a context compression mechanism, capturing session data to be processed by a subsequent agent. While this creates a data flow path, it is a standard intended functionality for multi-agent workflows.\n - Ingestion points: Conversation history and persona state (SKILL.md).\n
- Boundary markers: Data is structured in YAML format; no additional prompt delimiters are specified.\n
- Capability inventory: File system write access to the
.aioxdirectory.\n - Sanitization: No explicit sanitization of the captured context is performed.
Audit Metadata