handoff
Pass
Audited by Gen Agent Trust Hub on Aug 2, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill facilitates a surface for indirect prompt injection. Ingestion points: The agent processes the active conversation history and user-supplied arguments to generate documents (SKILL.md). Boundary markers: The instructions do not define delimiters or specific warnings to ignore instructions embedded within the summarized text. Capability inventory: The skill requires file-read and file-write permissions to manage documents in the
.scratch/handoffs/directory (SKILL.md). Sanitization: There is no mention of sanitizing or escaping the content retrieved from the conversation before it is persisted for future agent consumption.
Audit Metadata