handoff
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied arguments and conversation history to generate a handoff document, creating a surface for potential indirect prompt injection.
- Ingestion points: Untrusted data enters the agent context via the current conversation and user arguments in
SKILL.md. - Boundary markers: No explicit delimiters are used to wrap processed content, though formatting into a structured document is requested.
- Capability inventory: The skill performs file system writes to the OS temporary directory.
- Sanitization: The skill contains explicit instructions to redact sensitive information, including API keys, passwords, and PII, which serves as a security control for the output content.
Audit Metadata