handoff
Pass
Audited by Gen Agent Trust Hub on Mar 2, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill's functionality is limited to prompting the agent to summarize session progress, decisions, and next steps. No malicious instructions, prompt injection, or safety bypass attempts were found.
- [NO_CODE]: The skill is entirely composed of natural language instructions and Markdown templates. It does not include any scripts, binaries, or external dependencies, eliminating the risk of remote code execution or malicious dependency injection.
- [DATA_EXFILTRATION]: While the skill processes session history and code context, it only outputs this information to a local file path (
.claude/handoffs/). No network commands (such as curl or wget) or external domains are involved.
Audit Metadata