ito-handoff
Pass
Audited by Gen Agent Trust Hub on May 8, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill creates a handoff file that summarizes the current conversation context, which may include untrusted user input. If a user provides malicious instructions during the session, these could be persisted in the markdown file and potentially influence the behavior of the next AI session that reads it.
- Ingestion points: Current conversation context and optional user arguments in SKILL.md.
- Boundary markers: Absent. The instructions do not specify using delimiters or warnings to ignore embedded instructions within the handoff file.
- Capability inventory: File write operations to the
docs/ito-temp/handoff/directory (SKILL.md). - Sanitization: Absent. There are no explicit instructions to sanitize or filter the conversation content before writing it to the filesystem.
Audit Metadata