handoffs
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill summarizes the current conversation and user-provided purpose into a persistent handoff file, which acts as a surface for indirect prompt injection.
- Ingestion points: The entire conversation history and the
$ARGUMENTSvariable inSKILL.md. - Boundary markers: The instructions use
<purpose>and<analysis>tags to separate input and reasoning steps. - Capability inventory: The skill directs the agent to create the
.planning/handoffs/directory and write markdown files to the local file system. - Sanitization: There is no explicit sanitization or filtering mentioned for the aggregated conversation data before it is written to the handoff file.
Audit Metadata