handoff
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides instructions for summarizing a conversation into a handoff document. It does not contain any executable code, network operations, or obfuscation.
- [PROMPT_INJECTION]: The skill processes untrusted conversation history to generate output intended for another agent, creating a surface for indirect prompt injection.
- Ingestion points: Current conversation history (referenced in
SKILL.md). - Boundary markers: None explicitly defined in the prompt instructions.
- Capability inventory: The skill allows writing the resulting summary to the OS temporary directory.
- Sanitization: The instructions explicitly command the agent to redact sensitive information such as API keys, passwords, and PII before saving the document.
Audit Metadata